The emergence of the superposition mechanism in large language models is tied to training dynamics, which Zhu et al. (2025a) characterize as a two-stage process that allows the model to maintain multiple inference traces simultaneously.

Authors

• Person: Not available Organization: arXiv
  A Survey on the Theory and Mechanism of Large Language Models

Sources

• A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv via serper

Referenced by nodes (1)

• Large Language Models concept