© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 31726 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
31726

INDEX

Explanations

in

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

몇

-0.07

 Scientology

-0.06

nické

-0.06

 CENT

-0.06

ijo

-0.06

 دش

-0.06

-vis

-0.06

_SINGLE

-0.06

-user

-0.06

RNA

-0.06

POSITIVE LOGITS

.navigationController

0.07

UILTIN

0.06

 eyed

0.06

ワイト

0.06

.erase

0.06

 Sponsored

0.06

rooms

0.06

News

0.06

清

0.06

 offsetY

0.06

Activations Density 0.064%

No Known Activations