Winnie Yang

• Winnie Yang 23 Nov 2024 18:10 UTC

  1 point

  0

  on: Coup probes: Catch­ing catas­tro­phes with probes trained off-policy

  to do a do a

  There seem to by a typo here :)

• Winnie Yang 28 Aug 2024 16:44 UTC

  2 points

  0

  in reply to: Bogdan Ionut Cirstea’s comment on: De­cep­tion and Jailbreak Se­quence: 2. Iter­a­tive Refine­ment Stages of Jailbreaks in LLM

  Thank you so much for your interest and suggestion! Sorry this is a really rough draft… I didn’t have time to polish it yet. This is a good point! I might try make use of Claude’s help tonight!

De­cep­tion and Jailbreak Se­quence: 2. Iter­a­tive Refine­ment Stages of Jailbreaks in LLM

De­cep­tion and Jailbreak Se­quence: 1. Iter­a­tive Refine­ment Stages of De­cep­tion in LLMs

• Winnie Yang 2 Jun 2024 23:55 UTC

  1 point

  0

  on: Nor­mal­iz­ing Sparse Autoencoders

  Hi Hengyu! Really nice work here! I am wondering if you have released the pre-trained SAE for llama-2?