Open-weight refusal is one line away from off. Here is how we made it cost more.
Refusal in instruction-tuned LLMs lives in a single direction you can delete with a rank-1 edit. We post-trained Llama-3.2-1B-Instruct to spread that signal across many directions, raising the attack rank from K=1 to K≥16 with no measurable utility hit.
Read article