© 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 · 53015 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
53015

INDEX

Explanations

aph

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

iode

-0.07

 frec

-0.06

 fase

-0.06

比赛

-0.06

ım

-0.06

рд

-0.06

 parameters

-0.06

ruta

-0.06

(USER

-0.06

 descriptors

-0.06

POSITIVE LOGITS

aph

0.08

 confidential

0.07

 Summer

0.06

 ovar

0.06

sty

0.06

 compounded

0.06

�

0.06

 destabil

0.06

支

0.06

Scotland

0.06

Activations Density 0.001%

No Known Activations