© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 26560 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
26560

INDEX

Explanations

foreign languages

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

 рев

-0.06

 Parent

-0.06

.literal

-0.06

Parent

-0.06

チ

-0.06

 soil

-0.06

اطر

-0.06

 redundancy

-0.06

_reward

-0.06

/umd

-0.06

POSITIVE LOGITS

 meilleurs

0.07

 onKeyDown

0.06

LOS

0.06

woord

0.06

ujících

0.06

gets

0.06

】,【

0.06

los

0.06

'%$

0.06

Getty

0.06

Activations Density 0.083%

No Known Activations