Llama 3.3 70B Instruct

An 11-model probe puts the "this is impossible" signal 85 degrees from the refusal direction

Yucheng Du and Xiyang Hu report a single direction that separates answerable from unanswerable math and code prompts at 0.939 mean AUC across 11 models, and its mean cosine with the canonical safety-refusal direction is 0.087.