arxiv:2604.02608
Suhail Nadaf
suhailnadaf509
AI & ML interests
Mechanistic interpretability
Recent Activity
authored a paper about 1 month ago
Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens upvoted a paper about 1 month ago
Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens liked a model 6 months ago
google/gemma-scope-2Organizations
None yet