LLM-PT-interpret

AI & ML interests

None defined yet.

Recent Activity

amodaresi  authored a paper about 15 hours ago

Steering MoE LLMs via Expert (De)Activation

amodaresi  authored a paper about 15 hours ago

Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions

amodaresi  authored a paper 7 months ago

ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge

View all activity

Team members 2