© 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 · 7-RESID-POST-AA · 77895 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
77895

INDEX

Explanations

line

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

 عبد

-0.07

 أبو

-0.06

(Player

-0.06

 sucking

-0.06

 смог

-0.06

 hormone

-0.06

fö

-0.06

-0.06

ующий

-0.06

mph

-0.06

POSITIVE LOGITS

ponses

0.07

ﾝ

0.07

ry

0.06

(padding

0.06

YZ

0.06

<bits

0.06

 рез

0.06

Ell

0.06

Arr

0.06

imary

0.06

Activations Density 0.001%

No Known Activations