© 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 · 27-RESID-POST-AA · 19021 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
19021

INDEX

Explanations

information

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

 fractions

-0.08

 columns

-0.07

OUTH

-0.07

.dep

-0.07

plt

-0.07

 horizontal

-0.07

 field

-0.07

 whales

-0.07

 pressed

-0.06

alk

-0.06

POSITIVE LOGITS

่ร

0.07

_BROWSER

0.07

NSData

0.07

 Tổ

0.07

 μά

0.06

iselect

0.06

 histoire

0.06

ekce

0.06

加入

0.06

홍

0.06

Activations Density 0.032%

No Known Activations