© 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 · 52825 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
52825

INDEX

Explanations

members

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

 monuments

-0.07

ATABASE

-0.06

 notamment

-0.06

-0.06

季

-0.06

institution

-0.06

 Bunlar

-0.06

ании

-0.06

.Z

-0.06

 neur

-0.06

POSITIVE LOGITS

.Basic

0.07

(jq

0.07

.IC

0.07

#__

0.06

 glVertex

0.06

DD

0.06

adic

0.06

/close

0.06

rxjs

0.06

.getChild

0.06

Activations Density 0.019%

No Known Activations