© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 125130 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
125130

INDEX

Explanations

transistor

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

乾

-0.07

 feeder

-0.07

نج

-0.07

 zřejmě

-0.06

 Fraud

-0.06

 iddia

-0.06

 Blackjack

-0.06

 verwenden

-0.06

 Beng

-0.06

_ALT

-0.06

POSITIVE LOGITS

，将

0.06

repair

0.06

 maybe

0.06

 lightweight

0.06

 Freeze

0.06

#%

0.06

!!!!!

0.06

帮助

0.06

 */↵

0.06

 toutes

0.06

Activations Density 0.021%

No Known Activations