© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 94741 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
94741

INDEX

Explanations

chaperones

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

 LENGTH

-0.07

ΕΙ

-0.07

 Το

-0.07

ича

-0.07

 vibrations

-0.06

.........

-0.06

ыл

-0.06

FE

-0.06

 بیرون

-0.06

evice

-0.06

POSITIVE LOGITS

 champion

0.06

천

0.06

0.06

 advocacy

0.06

 červ

0.06

 chăm

0.06

 advocating

0.06

PageSize

0.06

Mock

0.06

 Corbyn

0.06

Activations Density 0.001%

No Known Activations