arxiv:2407.14561
Arnab Sen Sharma
sensharma
AI & ML interests
How LLMs represent knowledge and how they extract specific information from a latent? Can we perform update/delete/insert a concept into LLM in an human-interpretable way?
Recent Activity
upvoted
a
collection
about 1 month ago
Qwen3
updated
a model
6 months ago
sensharma/sae_llama-1B_layer-8_wiki-2M
updated
a model
6 months ago
sensharma/sae-disent_llama-1B_layer-8_wiki-2M
Organizations
None yet
