© 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 · 11-RESID-POST-AA · 37324 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
37324

INDEX

Explanations

control

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

 Hasan

-0.07

ecast

-0.06

aran

-0.06

Acceler

-0.06

 Sudan

-0.06

ostí

-0.06

선

-0.06

 signIn

-0.06

 Rows

-0.06

 Heard

-0.06

POSITIVE LOGITS

-esque

0.07

 trotz

0.07

TYPO

0.07

 freak

0.06

�

0.06

 noct

0.06

 tion

0.06

®

0.06

 dây

0.06

ћ

0.06

Activations Density 0.012%

No Known Activations