© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

LLAMA3.1-8B-IT · 27-RESID-POST-AA · 9642 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
9642

INDEX

Explanations

.

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

 sing

-0.07

 toJSON

-0.07

fullscreen

-0.06

 túi

-0.06

<=>

-0.06

	last

-0.06

 Harvey

-0.06

inn

-0.06

_PT

-0.06

 executable

-0.06

POSITIVE LOGITS

elly

0.06

.newLine

0.06

nen

0.06

 норматив

0.06

 privile

0.06

/NĐ

0.06

 MediaTek

0.06

oppel

0.06

tuy

0.05

民主

0.05

Activations Density 0.056%

No Known Activations