© 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 · 124368 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
124368

INDEX

Explanations

widow

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

-push

-0.07

QtCore

-0.07

_off

-0.07

_lens

-0.06

 sourced

-0.06

",$

-0.06

 newsp

-0.06

/workspace

-0.06

 illeg

-0.06

_entity

-0.06

POSITIVE LOGITS

 widow

0.09

 Widow

0.07

HUD

0.07

kov

0.06

дел

0.06

دام

0.06

tain

0.06

Dow

0.06

ibility

0.06

새

0.06

Activations Density 0.002%

No Known Activations