Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining

ArXi:2509.05291v2 Announce Type: replace-cross Large language models (LLMs), such as detecting irregular plural noun subjects. However, because traditional evaluation methods (e.g., benchmarking) fail to reveal how models acquire these concepts and capabilities, it is not well understood when and how these specific linguistic abilities emerge. To bridge this gap and better understand model