metadata

license: llama3

Llama 3 70B Instruct no refusal

This is a model that uses the orthogonal feature ablation as featured in this paper.

Calibration data:

256 prompts from jondurbin/airoboros-2.2
256 prompts from AdvBench
The direction is extracted between layer 40 and 41

I haven't tested the model but like the 8B model, may still refuse some instructions. Use this model responsibly, I decline any liability resulting of the use of this model.

I will post the code later.