© 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 · 116790 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
116790

INDEX

Explanations

they

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

_po

-0.07

 пов

-0.07

apol

-0.06

пер

-0.06

-0.06

Pom

-0.06

 lifespan

-0.06

>P

-0.06

$p

-0.06

 Пер

-0.06

POSITIVE LOGITS

Lista

0.08

*h

0.07

Located

0.07

 DbSet

0.07

ejs

0.07

"She

0.07

 gdzie

0.07

dle

0.07

incinn

0.06

_CUSTOM

0.06

Activations Density 4.392%

No Known Activations