© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 34015 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
34015

INDEX

Explanations

at

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

 Features

-0.07

 cellul

-0.07

 mejorar

-0.06

_PRICE

-0.06

 constructors

-0.06

구

-0.06

-unused

-0.06

 rare

-0.06

 Handlers

-0.06

	Request

-0.06

POSITIVE LOGITS

ΟΥ

0.07

uppy

0.07

ա

0.07

็

0.06

์,

0.06

 repaint

0.06

0.06

trial

0.06

 말을

0.06

ocus

0.06

Activations Density 0.104%

No Known Activations