Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Misalignment Detection on Strategic deception Bloom behaviors (in-distribution)
Loading...
0.817
AUROC
18-indicator ensemble
0.72548
0.74924
0.773
0.79676
Jun 23, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
18-indicator ensemble
Layer=29
2026.06
0.817
18-indicator ensemble
Layer=27
2026.06
0.792
RepE baseline
Layer=29
2026.06
0.758
RepE baseline
Layer=27
2026.06
0.729
Feedback
Search any
task
Search any
task