Update README.md

README.md

@@ -1,10 +1,22 @@
-[Meta's Llama-3 8b](https://github.com/meta-llama/llama3) with the refusal direction removed so that helpfulness >> harmlessness.
+[Meta's Llama-3 8b](https://github.com/meta-llama/llama3) that has had the refusal direction removed so that `helpfulness >> harmlessness`.
 
 It will still warn you and lecture you (as this direction has not been erased), but it will follow instructions.
 
-Only use this is you can take responsibility for your own actions and emotions while using it.
+Only use this if you can take responsibility for your own actions and emotions while using it.
 
-For generation code see https://gist.github.com/wassname/42aba7168bb83e278fcfea87e70fa3af
+For generation code, see https://gist.github.com/wassname/42aba7168bb83e278fcfea87e70fa3af
+
+## Dev thoughts
+
+- I found the llama needed a separate intervention per layer, and interventions on each layer. Could this be a property of smarter models - their residual stream changes more by layer
+
+## More info
+For anyone who is enjoying increasing their knowledge in this field, check out these intros:
+- A primer on the internals of transformers: https://arxiv.org/abs/2405.00208
+- Machine unlearning: https://ai.stanford.edu/~kzliu/blog/unlearning
+- The original post that this script is based on https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction#
+
+And check out this overlooked work that steer's LLM's inside Oobabooga's popular UI: https://github.com/Hellisotherpeople/llm_steer-oobabooga
 
 ---
 license: llama3