© 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 · 70979 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
70979

INDEX

Explanations

one

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

-0.06

Guy

-0.06

 later

-0.06

 clause

-0.06

-0.06

-0.06

Many

-0.06

 swiftly

-0.06

-0.06

-0.06

POSITIVE LOGITS

مة

0.07

 closeModal

0.07

 kesin

0.07

.Character

0.07

 운동

0.07

 zeit

0.07

_PAY

0.06

ví

0.06

 imagin

0.06

 موقعیت

0.06

Activations Density 0.013%

No Known Activations