© 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 · 7-RESID-POST-AA · 21481 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
21481

INDEX

Explanations

disgust

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

Negative Logits

 steady

-0.07

 simple

-0.06

lap

-0.06

Head

-0.06

 food

-0.06

-0.06

 armor

-0.06

 obedient

-0.06

arlo

-0.06

getChild

-0.06

POSITIVE LOGITS

 disgusting

0.13

 disgust

0.11

 disgusted

0.10

BUG

0.08

hex

0.07

IGN

0.07

rev

0.07

ｌ

0.06

 Baron

0.06

 Jenkins

0.06

Activations Density 0.010%

No Known Activations