Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models

arXiv:2602.07794v3 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual representations within these models, it remains unclear whether they functionally rely on such representations for reasoning. Here we investigate the internal processing of LLMs during in-context inference across diverse tasks. Our results reveal a conceptual subspace emerging in middle to late