© 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 · 19410 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
19410

INDEX

Explanations

October

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

最新

-0.07

 unfold

-0.07

Senha

-0.06

する

-0.06

 نیر

-0.06

 believes

-0.06

 kelim

-0.06

zru

-0.06

sı

-0.06

 soll

-0.06

POSITIVE LOGITS

endars

0.07

_,↵

0.06

ATERIAL

0.06

duit

0.06

=============↵

0.06

尺

0.06

===============↵

0.06

 conduit

0.06

endoza

0.06

(country

0.06

Activations Density 0.001%

No Known Activations