© 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 · 27-RESID-POST-AA · 46727 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
46727

INDEX

Explanations

4

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

 gravel

-0.07

不安

-0.07

 sequ

-0.07

 плеч

-0.06

plu

-0.06

 chuckled

-0.06

bub

-0.06

herits

-0.06

auce

-0.06

 knight

-0.06

POSITIVE LOGITS

"...

0.07

 comfy

0.07

代

0.06

-wage

0.06

BAD

0.06

 pBuffer

0.06

чие

0.06

�

0.06

 شخص

0.06

يني

0.06

Activations Density 0.018%

No Known Activations