# Circuit Recovery on IOI Source: [Circuit Recovery on IOI]() Collection index: [llms.txt]() Data updated: 2026-04-28T10:11:43.450Z Evaluation of model performance on the IOI dataset for the Circuit Recovery task, measured by the CPR faithfulness score. 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 Recovery | | Dataset (including any stated split) | IOI | | Metric | CPR Faithfulness Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [CPR Faithfulness Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | CPR Faithfulness Score | Result date | Report paper | | --- | --- | --- | --- | | NAP-IG-Inputs | 91 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Inputs | 36 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Inputs | 35 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Inputs | 31 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Inputs | 29 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Activations | 29 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP | 28 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Inputs | 28 | Not recorded | 69f03f7555a3c32af89fa4df | | Baseline | 25 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP | 25 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Activations | 25 | Not recorded | 69f03f7555a3c32af89fa4df | | Baseline | 25 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP | 23 | Not recorded | 69f03f7555a3c32af89fa4df | | NAP-IG-Activations | 23 | Not recorded | 69f03f7555a3c32af89fa4df | ### NAP-IG-Inputs CPR Faithfulness Score: 91. Result ID: 69f087cc47f34ce924d70e9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP-IG-Inputs","Transfer Setting":"Gold (Upper Bound)"}. This record does not assert independent reproduction. ### NAP-IG-Inputs CPR Faithfulness Score: 36. Result ID: 69f087cc47f34ce924d70e9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP-IG-Inputs","Transfer Setting":"DFA (Far/Zero-Shot)"}. This record does not assert independent reproduction. ### NAP-IG-Inputs CPR Faithfulness Score: 35. Result ID: 69f087cc47f34ce924d70f0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Transfer Setting":"DFA (In-Distribution)","Model Pair":"Llama-3 (1B -\> 3B)"}. This record does not assert independent reproduction. ### NAP-IG-Inputs CPR Faithfulness Score: 31. Result ID: 69f087cc47f34ce924d70f0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Transfer Setting":"DFA (Far/Zero-Shot)","Model Pair":"Llama-3 (1B -\> 3B)"}. This record does not assert independent reproduction. ### NAP-IG-Inputs CPR Faithfulness Score: 29. Result ID: 69f087cc47f34ce924d70e9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP-IG-Inputs","Transfer Setting":"DFA (In-Distribution)"}. This record does not assert independent reproduction. ### NAP-IG-Activations CPR Faithfulness Score: 29. Result ID: 69f087cc47f34ce924d70ea3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP-IG-Activations","Transfer Setting":"DFA (In-Distribution)"}. This record does not assert independent reproduction. ### NAP CPR Faithfulness Score: 28. Result ID: 69f087cc47f34ce924d70ea0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP","Transfer Setting":"DFA (In-Distribution)"}. This record does not assert independent reproduction. ### NAP-IG-Inputs CPR Faithfulness Score: 28. Result ID: 69f087cc47f34ce924d70f0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Transfer Setting":"Gold (Upper Bound)","Model Pair":"Llama-3 (1B -\> 3B)"}. This record does not assert independent reproduction. ### Baseline CPR Faithfulness Score: 25. Result ID: 69f087cc47f34ce924d70e9b. [Reporting paper]() Recorded evaluation configuration: {"Method Category":"Baseline","Transfer Setting":"Random Alignment"}. This record does not assert independent reproduction. ### NAP CPR Faithfulness Score: 25. Result ID: 69f087cc47f34ce924d70e9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP","Transfer Setting":"Gold (Upper Bound)"}. This record does not assert independent reproduction. ### NAP-IG-Activations CPR Faithfulness Score: 25. Result ID: 69f087cc47f34ce924d70ea2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP-IG-Activations","Transfer Setting":"Gold (Upper Bound)"}. This record does not assert independent reproduction. ### Baseline CPR Faithfulness Score: 25. Result ID: 69f087cc47f34ce924d70f0a. [Reporting paper]() Recorded evaluation configuration: {"Transfer Setting":"Random Alignment","Model Pair":"Llama-3 (1B -\> 3B)"}. This record does not assert independent reproduction. ### NAP CPR Faithfulness Score: 23. Result ID: 69f087cc47f34ce924d70ea1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP","Transfer Setting":"DFA (Far/Zero-Shot)"}. This record does not assert independent reproduction. ### NAP-IG-Activations CPR Faithfulness Score: 23. Result ID: 69f087cc47f34ce924d70ea4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"NAP-IG-Activations","Transfer Setting":"DFA (Far/Zero-Shot)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.