# Circuit Localization on Mixing dataset All tasks Source: [Circuit Localization on Mixing dataset All tasks]() Collection index: [llms.txt]() Data updated: 2026-05-12T11:18:36.397Z Evaluation of model performance on the Circuit Localization task using the Mixing dataset All tasks, reporting the CMD metric. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Circuit Localization | | Dataset (including any stated split) | Mixing dataset All tasks | | Metric | CMD | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 28 of 28 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [CMD](): Lower is better; unit: SCALAR. ## Recorded results | Method | CMD | Result date | Report paper | | --- | --- | --- | --- | | K-Random | 0.007 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-SVD | 0.007 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-PCA | 0.007 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-divisive-SVD | 0.008 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-agglom.-SVD | 0.01 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-representative | 0.012 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-divisive-SVD | 0.018 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-agglom.-SVD | 0.019 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-SVD | 0.019 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-PCA | 0.02 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP-IG | 0.022 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-Random | 0.027 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-divisive-SVD | 0.03 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-PCA | 0.039 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-Random | 0.041 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP | 0.042 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-SVD | 0.043 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-agglom.-SVD | 0.061 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP-IG | 0.065 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-representative | 0.067 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-representative | 0.093 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP | 0.114 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP-IG | 0.13 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP | 0.149 | Not recorded | 6a02b45cdbc836b87d8249e8 | | E-Act | 0.307 | Not recorded | 6a02b45cdbc836b87d8249e8 | | Random | 0.712 | Not recorded | 6a02b45cdbc836b87d8249e8 | | Random | 0.747 | Not recorded | 6a02b45cdbc836b87d8249e8 | | Random | 0.752 | Not recorded | 6a02b45cdbc836b87d8249e8 | ### K-Random CMD: 0.007. Result ID: 6a030c7d47f34ce924e6cbee. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-kmeans-SVD CMD: 0.007. Result ID: 6a030c7d47f34ce924e6cbfa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-kmeans-PCA CMD: 0.007. Result ID: 6a030c7d47f34ce924e6cbfd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-divisive-SVD CMD: 0.008. Result ID: 6a030c7d47f34ce924e6cbf7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-agglom.-SVD CMD: 0.01. Result ID: 6a030c7d47f34ce924e6cbf4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### K-representative CMD: 0.012. Result ID: 6a030c7d47f34ce924e6cbf1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-divisive-SVD CMD: 0.018. Result ID: 6a030c7d47f34ce924e6cbf8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-agglom.-SVD CMD: 0.019. Result ID: 6a030c7d47f34ce924e6cbf5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-kmeans-SVD CMD: 0.019. Result ID: 6a030c7d47f34ce924e6cbfb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-kmeans-PCA CMD: 0.02. Result ID: 6a030c7d47f34ce924e6cbfe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### EAP-IG CMD: 0.022. Result ID: 6a030c7d47f34ce924e6cbe4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### K-Random CMD: 0.027. Result ID: 6a030c7d47f34ce924e6cbef. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-divisive-SVD CMD: 0.03. Result ID: 6a030c7d47f34ce924e6cbf6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### DCD-kmeans-PCA CMD: 0.039. Result ID: 6a030c7d47f34ce924e6cbfc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### K-Random CMD: 0.041. Result ID: 6a030c7d47f34ce924e6cbed. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP CMD: 0.042. Result ID: 6a030c7d47f34ce924e6cbe7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-kmeans-SVD CMD: 0.043. Result ID: 6a030c7d47f34ce924e6cbf9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### DCD-agglom.-SVD CMD: 0.061. Result ID: 6a030c7d47f34ce924e6cbf3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP-IG CMD: 0.065. Result ID: 6a030c7d47f34ce924e6cbe5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### K-representative CMD: 0.067. Result ID: 6a030c7d47f34ce924e6cbf2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### K-representative CMD: 0.093. Result ID: 6a030c7d47f34ce924e6cbf0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP CMD: 0.114. Result ID: 6a030c7d47f34ce924e6cbe8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### EAP-IG CMD: 0.13. Result ID: 6a030c7d47f34ce924e6cbe3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP CMD: 0.149. Result ID: 6a030c7d47f34ce924e6cbe6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### E-Act CMD: 0.307. Result ID: 6a030c7d47f34ce924e6cbe9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### Random CMD: 0.712. Result ID: 6a030c7d47f34ce924e6cbea. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### Random CMD: 0.747. Result ID: 6a030c7d47f34ce924e6cbeb. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### Random CMD: 0.752. Result ID: 6a030c7d47f34ce924e6cbec. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.