Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Output-based feature description evaluation on Llama Instruct MLP features 3.1
Loading...
45.8
Score
VocabProj
36.544
38.947
41.35
43.753
Jan 14, 2025
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
VocabProj
2025.01
45.8
Ensemble Concat
combination=All
2025.01
44.6
Ensemble Raw
combination=VP+TC
2025.01
44.3
TokenChange
2025.01
43.8
Ensemble Raw
combination=All
2025.01
41.8
Ensemble Raw
combination=MA+TC
2025.01
41.7
Ensemble Raw
combination=MA+VP
2025.01
40.7
MaxAct++
2025.01
39
MaxAct
2025.01
36.9
Feedback
Search any
task
Search any
task