© 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 · 73400 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
73400

INDEX

Explanations

.Nullable

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

ldb

-0.06

amanho

-0.06

 crane

-0.06

 phrase

-0.06

-hot

-0.06

洗

-0.06

'(

-0.06

-prefix

-0.06

 Spring

-0.06

omite

-0.06

POSITIVE LOGITS

ушка

0.07

IRC

0.07

 Bluetooth

0.07

 Stark

0.06

.Ui

0.06

 salud

0.06

 му

0.06

ازات

0.06

мовір

0.06

 paired

0.06

Activations Density 0.001%

No Known Activations