© 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 · 15-RESID-POST-AA · 20400 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20400

INDEX

Explanations

on

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 crispy

-0.07

archs

-0.06

 корп

-0.06

.Areas

-0.06

thest

-0.06

 años

-0.06

。。

-0.06

Ars

-0.06

.getNumber

-0.06

 WEST

-0.06

POSITIVE LOGITS

productive

0.06

/temp

0.06

parms

0.06

�

0.06

/react

0.06

 glob

0.06

臺

0.06

 chang

0.06

nov

0.06

WithType

0.06

Activations Density 0.155%

No Known Activations