© 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 · 11-RESID-POST-AA · 34203 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
11-RESID-POST-AA
34203

INDEX

Explanations

Legal case numbers

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

üç

-0.06

Hen

-0.06

Dé

-0.06

 Méd

-0.06

ат

-0.06

quer

-0.06

 pork

-0.06

Hen

-0.06

 영어

-0.06

,nil

-0.06

POSITIVE LOGITS

Urban

0.07

ражд

0.07

Who

0.06

(baseUrl

0.06

 education

0.06

 coorden

0.06

 Fuck

0.06

Global

0.06

 register

0.06

.fragment

0.06

Activations Density 0.007%

No Known Activations