© 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 · 127885 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
127885

INDEX

Explanations

/or

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

 Ninth

-0.07

emodel

-0.06

 boilers

-0.06

DataTable

-0.06

 fich

-0.06

atem

-0.06

-0.06

TR

-0.06

_TH

-0.06

icrous

-0.06

POSITIVE LOGITS

 dipl

0.07

 flush

0.06

 Subscribe

0.06

оду

0.06

.auth

0.06

 rented

0.06

 onSelect

0.06

 довольно

0.06

Max

0.06

oloj

0.06

Activations Density 0.001%

No Known Activations