© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 27-RESID-POST-AA · 23607 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
23607

INDEX

Explanations

mentions "bay"

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

Negative Logits

 interested

-0.07

zi

-0.07

impl

-0.07

como

-0.06

-0.06

 :
↵

-0.06

(Boolean

-0.06

lage

-0.06

builders

-0.06

totalCount

-0.06

POSITIVE LOGITS

 extraordinarily

0.08

<Vec

0.06

/NĐ

0.06

 моб

0.06

	Null

0.06

 Заг

0.06

 Krak

0.06

 ICMP

0.06

_mt

0.05

/TT

0.05

Activations Density 0.023%

No Known Activations