© 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 · 79123 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
79123

INDEX

Explanations

pronouns

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

 wont

-0.07

iembre

-0.06

_answers

-0.06

ерк

-0.06

 існу

-0.06

远

-0.06

 getInstance

-0.06

람

-0.06

 CONT

-0.06

 actionPerformed

-0.06

POSITIVE LOGITS

좀

0.07

 counseling

0.07

IL

0.07

 onCancel

0.07

ै?↵

0.06

swe

0.06

dn

0.06

]]>

0.06

ζί

0.06

us

0.06

Activations Density 0.089%

No Known Activations