Safety
attention
Attention weights how much each token should attend to others when producing representations.
Expanded definition
attention shows up constantly when teams ship LLM features. Practically, it influences how you design prompts, evaluate quality, and reason about failure modes. Teams should document how attention manifests in their stack—data handling, evaluation, and runtime guardrails—and revisit assumptions as models update.
Related terms
Explore adjacent ideas in the knowledge graph.