The Kinematics of Factual Commitment in Llama 3.1-8B
Hi LessWrong, I'm a 17yo independent researcher and this is my first real research in this field. I isolated a kinematic transition vector at Layer 15 that predicts factual correctness with 0.95 AUROC. Would love some good feedback! Crossposted from my substack. I wondered: Do LLMs even have any representation...
May 91