© 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 · 15-RESID-POST-AA · 33833 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
33833

INDEX

Explanations

programming code and soccer

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

ху

-0.08

-0.07

.un

-0.07

 Fern

-0.06

Cul

-0.06

Bur

-0.06

SOR

-0.06

-0.06

 Со

-0.06

.r

-0.06

POSITIVE LOGITS

(audio

0.06

truck

0.06

 العلم

0.06

Different

0.06

 stesso

0.06

Ik

0.06

.Close

0.06

会社

0.06

Speech

0.06

 speaking

0.06

Activations Density 0.001%

No Known Activations