Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Neuron Labeling on SAE-TopK neurons

35.23SCS Score

LE

29.073230.671632.2733.8684Apr 24, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
35.23
2026.04
35.01
2026.04
34.37
2026.04
31.91
2026.04
31.6
2026.04
31.46
2026.04
31.28
2026.04
31.24
2026.04
30.79
2026.04
30.71
2026.04
30.59
2026.04
30.33
2026.04
30.19
2026.04
29.67
2026.04
29.31