© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 93636 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
93636

INDEX

Explanations

form

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

ero

-0.07

rze

-0.07

anno

-0.07

beros

-0.06

 Jesse

-0.06

ワイト

-0.06

_HEAD

-0.06

 Bristol

-0.06

 Bangalore

-0.06

친

-0.06

POSITIVE LOGITS

_media

0.07

 pedals

0.06

Parameters

0.06

 Scalars

0.06

']>;↵

0.06

里

0.06

 encore

0.06

 основных

0.06

 glitches

0.06

 grav

0.06

Activations Density 0.017%

No Known Activations