© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 72444 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
72444

INDEX

Explanations

as

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 voks

-0.06

(),

-0.06

 compound

-0.06

 institution

-0.06

onian

-0.06

straction

-0.06

hi

-0.06

 przy

-0.06

/post

-0.06

 birlikte

-0.06

POSITIVE LOGITS

ानस

0.06

KN

0.06

Checks

0.06

 характер

0.06

tern

0.06

MV

0.06

(vc

0.06

SR

0.06

 hız

0.06

 leaderboard

0.06

Activations Density 0.020%

No Known Activations