© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 46263 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
46263

INDEX

Explanations

royalty

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

الي

-0.07

Kan

-0.07

něn

-0.06

_channels

-0.06

Chu

-0.06

 Johns

-0.06

ansible

-0.06

.dis

-0.06

_mas

-0.06

emsp

-0.06

POSITIVE LOGITS

ослав

0.07

 tess

0.06

ih

0.06

.setScale

0.06

_rx

0.06

(Class

0.06

θερ

0.06

 Deploy

0.06

TO

0.06

[[

0.06

Activations Density 0.005%

No Known Activations