---
title: "linear representation hypothesis"
type: "entity"
entity_kind: "concept"
status: "hub"
canonical_name: "linear representation hypothesis"
aliases: []
first_seen: "2026-07-17T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["intrinsic dimension","safety alignment","jailbreak / activation engineering","large language models"]
---


The claim that many concepts an LLM represents internally correspond to linear directions in its activation space — a distinct geometric object from a fine-tuning run's weight-space intrinsic dimension (see [[entity-intrinsic-dimension]] for the boundary this vault deliberately holds between the two). Entered this vault via [[claim-teo-2025-linear-safety-structure-grows-with-model-size]]: such linear structure is described as emergent, present only in models "sufficiently large, with high-dimensional representations," and is the mechanism exploited by activation-engineering jailbreaks — so the same scale that makes a model easier to fine-tune (falling intrinsic dimension) does not make its activation space less exploitable; if anything the opposite.

## References
- [[claim-teo-2025-linear-safety-structure-grows-with-model-size]]
- [[question-intrinsic-dimension-falls-with-model-scale-adaptation]]