Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Feature Explanation Generation on Llama3.1-8b SAE llamascope-res-32k Layer 1
Loading...
58.4
GEN
SAEExplainer
30.0808
37.4329
44.785
52.1371
Jun 7, 2026
GEN
INP
OUT
Ahigh
Alow
∆A
Updated 1mo ago
Evaluation Results
Method
Method
Links
GEN
INP
OUT
Ahigh
Alow
∆A
SAEExplainer
2026.06
58.4
68
76
7.19
0.01
7.18
N-pedia w/ Claude
Generator=Claude Sonne...
2026.06
55.67
61.33
71.66
6.52
0.03
6.49
N-pedia w/ GPT-5
Generator=GPT-5
2026.06
54.47
63.33
70
6.5
0.02
6.48
Neuronpedia
Generator=GPT-4o-mini
2026.06
33.93
49
69.33
4.56
0.02
4.54
Activation Oracles
2026.06
31.17
41.67
70.67
3.89
0.06
3.83
Feedback
Search any
task
Search any
task