© 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 · 15-RESID-POST-AA · 126785 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
126785

INDEX

Explanations

to

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

"strings

-0.07

 kuruluş

-0.06

 أخرى

-0.06

 Cater

-0.06

 atlas

-0.06

 různých

-0.06

 uploader

-0.06

@include

-0.06

dag

-0.06

cmd

-0.06

POSITIVE LOGITS

WI

0.07

 towards

0.07

DMI

0.06

 OutputStream

0.06

 misses

0.06

ovid

0.06

phins

0.06

fill

0.06

역

0.06

 krás

0.06

Activations Density 0.012%

No Known Activations