© 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 · 69269 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
69269

INDEX

Explanations

table

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

formik

-0.07

 drink

-0.07

 выз

-0.07

 compound

-0.07

ymce

-0.07

drink

-0.07

 modest

-0.06

.BAD

-0.06

Bond

-0.06

_CONTROLLER

-0.06

POSITIVE LOGITS

iglia

0.06

iể

0.06

witter

0.06

Intersection

0.06

.ob

0.06

 Cortex

0.06

 targ

0.06

EC

0.06

addir

0.06

-tier

0.05

Activations Density 0.031%

No Known Activations