© 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 · 23-RESID-POST-AA · 7644 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
23-RESID-POST-AA
7644

INDEX

Explanations

roph

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

SUB

-0.06

 cyber

-0.06

rhe

-0.06

 подраз

-0.06

 newInstance

-0.06

 Inform

-0.06

股票

-0.06

 societal

-0.06

elen

-0.05

<hr

-0.05

POSITIVE LOGITS

 possessions

0.07

xac

0.07

ümüzde

0.06

0.06

Events

0.06

 trag

0.06

 Rich

0.06

0.06

 پزش

0.06

 pains

0.06

Activations Density 0.000%

No Known Activations