© 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 · 63351 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
63351

INDEX

Explanations

Pytorch and wind

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

 sabot

-0.08

zug

-0.07

র

-0.07

HRESULT

-0.07

uell

-0.07

Maintenance

-0.07

 sinon

-0.06

ř

-0.06

 reimburse

-0.06

azel

-0.06

POSITIVE LOGITS

學

0.07

ouncill

0.06

(↵

0.06

み

0.06

 legally

0.06

祝

0.06

 comforting

0.06

 optim

0.06

 Во

0.06

 Loop

0.05

Activations Density 0.000%

No Known Activations