SourceRevisiting In-context Learning Inference Circuit in Large Language Models
The paper identifies induction heads (attention heads with high scores from label tokens to the query forerunner) in Llama 3 70B and finds that more than half are not 'correct' (do not preferentially attend to the correct label). Correct induction heads show significant but incomplete overlap across the 6 evaluation datasets (e.g., 0.83 overlap between SST-2 and MR, 0.55 between SST-2 and AG News), indicating a mix of task-inherent and task-specific subspaces. PCA visualization of label representations mapped through the best induction head (correct rate 0.95) shows that attention assignment morphology changes significantly from k=1 to k=2 demonstrations but stabilizes from k=15 to k=16, explaining the submodular improvement and saturation of ICL performance with more demonstrations.