© 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 · 27-RESID-POST-AA · 110251 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
27-RESID-POST-AA
110251

INDEX

Explanations

colon

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

 conformity

-0.07

 nowrap

-0.07

ğu

-0.06

>↵↵↵

-0.06

 Vita

-0.06

—

-0.06

Nov

-0.06

فهوم

-0.06

 vinyl

-0.06

/colors

-0.06

POSITIVE LOGITS

break

0.06

 nuis

0.06

_DL

0.06

_blocked

0.06

ething

0.06

eurs

0.06

 aumento

0.06

teacher

0.06

our

0.06

 дів

0.06

Activations Density 0.001%

No Known Activations