© 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 · 40693 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
40693

INDEX

Explanations

a

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

leftrightarrow

-0.07

การจ

-0.06

�

-0.06

CppMethod

-0.06

ену

-0.06

mıştı

-0.06

_STR

-0.06

CHE

-0.06

 tedy

-0.06

у

-0.06

POSITIVE LOGITS

Letter

0.07

 bgColor

0.07

 Come

0.06

 WELL

0.06

FIX

0.06

 brings

0.06

 files

0.06

_MEDIUM

0.06

flows

0.06

_lowercase

0.06

Activations Density 0.062%

No Known Activations