© 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 · 35796 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
35796

INDEX

Explanations

small, approximation

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

-0.07

-pe

-0.07

 بين

-0.06

_sel

-0.06

_EOL

-0.06

Xi

-0.06

 setObject

-0.06

Anime

-0.06

 Armenian

-0.06

_assoc

-0.06

POSITIVE LOGITS

.recipe

0.06

0.06

っても

0.06

0.06

izzare

0.06

0.06

acist

0.06

.eulerAngles

0.06

 pořád

0.06

////////////////////////////////

0.06

Activations Density 0.137%

No Known Activations