Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Textual Concept Interpretability on LLaVA-NeXT textual concepts
Loading...
81
Detection Score
Llama 3.1
75.8
77.15
78.5
79.85
Jun 19, 2026
Detection Score
Fuzziness Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Detection Score
Fuzziness Score
Llama 3.1
Model Size=8b
2026.06
81
83
LLaVA
Framework=Multidata_SAE
2026.06
78
80
Gemma 2
Model Size=9b
2026.06
76
74
Feedback
Search any
task
Search any
task
