© 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 · 19-RESID-POST-AA · 58975 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
58975

INDEX

Explanations

Rome

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

SW

-0.07

flows

-0.07

Nej

-0.06

 Activ

-0.06

 kriz

-0.06

Heavy

-0.06

-स

-0.06

keyword

-0.06

 bears

-0.06

Educ

-0.06

POSITIVE LOGITS

 Rome

0.08

 Roma

0.08

 行政

0.07

 Mime

0.07

iffin

0.07

0.07

ishlist

0.06

ishops

0.06

ポート

0.06

.stream

0.06

Activations Density 0.006%

No Known Activations