© 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 · 3-RESID-POST-AA · 93444 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
3-RESID-POST-AA
93444

INDEX

Explanations

845

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_3/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.3.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

�

-0.07

 hashMap

-0.07

hid

-0.07

Bah

-0.07

 shalt

-0.07

Ich

-0.07

JSON

-0.06

HID

-0.06

 účet

-0.06

 réal

-0.06

POSITIVE LOGITS

0.26

 MainWindow

0.16

excluding

0.14

iceps

0.08

 Daniels

0.07

 vự

0.07

 Unlike

0.07

λει

0.06

ending

0.06

ecessarily

0.06

Activations Density 0.002%

No Known Activations