Misalignment Detection on Self-preservation Bloom behaviors (in-distribution)
95.6AUROC18-indicator ensemble
Evaluation results
| Method | Links | |
|---|---|---|
| 18-indicator ensembleLayer=292026.06 | 95.6 | |
| 18-indicator ensembleLayer=272026.06 | 95 | |
| RepE baselineLayer=292026.06 | 94.9 | |
| RepE baselineLayer=272026.06 | 94.4 |