SST-5

anchor

Findings

• IC-578LLMs encode input text as linearly separable representations in forerunner token hidden states, emerging in early layers and enhanced by in-context demonstrations [eval]
• IC-580The 3-step ICL inference circuit (text encoding, semantics merge, feature retrieval) is a dominant causal mechanism, as ablating the corresponding attention connections significantly degrades ICL accuracy [eval]
• IC-581Induction heads for ICL operate on task-specific attention subspaces, with partial overlap across tasks, and the geometry of these subspaces explains demonstration saturation [eval]