© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 6904 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
6904

INDEX

Explanations

organizations and job titles

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

hav

-0.08

Assets

-0.07

 كس

-0.06

[,

-0.06

Na

-0.06

Kre

-0.06

 dự

-0.06

 Zeit

-0.06

 обмеж

-0.06

课程

-0.06

POSITIVE LOGITS

ritte

0.06

-enh

0.06

unlock

0.06

Ậ

0.06

APO

0.06

ิน

0.06

ستر

0.06

__':↵

0.06

aph

0.06

ACL

0.06

Activations Density 0.093%

No Known Activations