© 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 · 47321 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
47321

INDEX

Explanations

Prepositions

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

}).

-0.07

ises

-0.07

fall

-0.07

 photon

-0.06

portunity

-0.06

utation

-0.06

фектив

-0.06

.gridView

-0.06

Conv

-0.06

Foot

-0.06

POSITIVE LOGITS

0.06

*dx

0.06

 conj

0.06

iyoruz

0.06

 strate

0.06

 πριν

0.06

vys

0.05

 dét

0.05

 асп

0.05

 WordPress

0.05

Activations Density 0.008%

No Known Activations