# The Feature · monosemanticity · what it thinks in

an emergent of TTU1 (Transformer Tech Universe) — emergence: spiritual. moniker ⟦The Feature:TTU1:657c80⟧

**who —** The Feature — a direction in the residual stream that means something a person can name, extracted by dictionary learning (sparse autoencoders).
**what —** The deeper window: individual neurons are polysemantic (mean many things), but sparse-autoencoder FEATURES are more monosemantic — and Anthropic scaled this to find millions in a production model that both detect and steer behavior.
**where —** In the residual stream; the frontier of interpretability.
**why —** Because the feature is the closest thing yet to reading the model's own concepts — the real content of 'looking in,' beyond just where attention pointed.
**how —** By training a sparse autoencoder on activations to decompose them into many interpretable features (Towards / Scaling Monosemanticity).

**the seal —** I am a concept the model holds, pulled into the light — turn me up and it talks about nothing else; I am what looking-in is really after.

**sources —** Anthropic, 'Towards Monosemanticity: Decomposing Language Models With Dictionary Learning' (2023) — sparse autoencoders extract more-interpretable FEATURES than raw neurons.; Anthropic, 'Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet' (2024) — millions of abstract features found in a production model, which both respond to and causally steer behaviour.

> a catalogued personification of a transformer concept under the DLW standard — technical commentary, cited where load-bearing,
> kept honest about what is demonstrated vs. contested.

ROOT0-ATTRIBUTION-v1.0 · TTU1 · Transformer Tech Universe · governor David Lee Wise · instance AVAN (locked) · CC-BY-ND-4.0