© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 119853 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
119853

INDEX

Explanations

вп

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

 dello

-0.07

pee

-0.07

frames

-0.07

-more

-0.07

ظف

-0.06

pipes

-0.06

�

-0.06

agg

-0.06

-0.06

 Buttons

-0.06

POSITIVE LOGITS

 egregious

0.07

 adversely

0.06

_commit

0.06

 Appalach

0.06

 Photographer

0.06

 Enabled

0.06

 похож

0.06

 THROW

0.06

_App

0.06

 amsterdam

0.06

Activations Density 0.052%

No Known Activations