AliceThirty's picture
Update README.md
485e562 verified

I used the Orthogonal Activation Steering method on Llama-3-Smaug-8B as an attempt to remove its refusal.
I used the following script https://gist.github.com/wassname/42aba7168bb83e278fcfea87e70fa3af
with the following dataset https://huggingface.co/datasets/Undi95/orthogonal-activation-steering-TOXIC
Original model: https://huggingface.co/abacusai/Llama-3-Smaug-8B