© 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 · 10418 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
10418

INDEX

Explanations

on

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

lamaz

-0.06

.locale

-0.06

 convincing

-0.06

 proteins

-0.06

.setScale

-0.06

RefCount

-0.06

น

-0.06

IH

-0.06

اوية

-0.06

.jp

-0.06

POSITIVE LOGITS

0.07

tie

0.07

+lsi

0.07

 จาก

0.07

pk

0.07

 خوبی

0.07

 Nazi

0.06

_travel

0.06

usa

0.06

(st

0.06

Activations Density 0.030%

No Known Activations