© 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 · 19-RESID-POST-AA · 72868 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
72868

INDEX

Explanations

,

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

_friend

-0.07

!↵

-0.06

 bets

-0.06

Compar

-0.06

 attr

-0.06

്

-0.06

рост

-0.06

�

-0.06

pew

-0.06

thresh

-0.06

POSITIVE LOGITS

义

0.07

-efficient

0.07

gment

0.07

volution

0.06

Sorted

0.06

 CSRF

0.06

 branching

0.06

작

0.06

 inefficient

0.06

asure

0.06

Activations Density 2.881%

No Known Activations