© 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 · 11-RESID-POST-AA · 51207 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
51207

INDEX

Explanations

prob

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

++){↵

-0.07

 الجم

-0.06

 чуть

-0.06

عار

-0.06

ิทยาล

-0.06

adult

-0.05

 řadu

-0.05

-0.05

 týden

-0.05

كو

-0.05

POSITIVE LOGITS

 techniques

0.07

isí

0.07

論

0.07

불

0.07

_RESPONSE

0.07

START

0.06

 آپ

0.06

vements

0.06

 Scientific

0.06

 contribute

0.06

Activations Density 0.001%

No Known Activations