© 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 · 62392 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
62392

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

 próxima

-0.07

 descricao

-0.06

 dared

-0.06

rtype

-0.06

.View

-0.06

_AB

-0.06

ρεια

-0.06

álně

-0.06

 수가

-0.06

ération

-0.06

POSITIVE LOGITS

 EXPER

0.07

ξ

0.07

')]↵

0.07

"]
↵

0.06

Omn

0.06

Cb

0.06

xm

0.06

ω

0.06

0.06

Col

0.06

Activations Density 0.006%

No Known Activations