© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 46848 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
46848

INDEX

Explanations

vowel

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

 find

-0.06

'})↵

-0.06

 Express

-0.06

 Marc

-0.06

Express

-0.06

Employ

-0.06

atabase

-0.06

 calculate

-0.06

 inspirational

-0.06

})↵

-0.06

POSITIVE LOGITS

 vowels

0.10

 vowel

0.09

しよう

0.07

0.07

vio

0.07

ัญ

0.07

 вертик

0.07

 отверсти

0.07

vw

0.06

 kullanılan

0.06

Activations Density 0.001%

No Known Activations