© 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 · 27-RESID-POST-AA · 46455 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
46455

INDEX

Explanations

another language (Russian?)

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

 احتم

-0.07

рами

-0.07

 Outreach

-0.06

 Shir

-0.06

Lines

-0.06

信

-0.06

 θεω

-0.06

 Methods

-0.06

comings

-0.06

UME

-0.06

POSITIVE LOGITS

imension

0.07

_sta

0.07

mue

0.07

 일을

0.06

vyh

0.06

)--

0.06

》

0.06

.__

0.06

_least

0.06

 tòa

0.06

Activations Density 0.073%

No Known Activations