© 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 · 11-RESID-POST-AA · 18610 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
18610

INDEX

Explanations

code

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

دان

-0.07

_instruction

-0.07

WhatsApp

-0.06

movies

-0.06

μμα

-0.06

prev

-0.06

ani

-0.06

Coords

-0.06

tiles

-0.06

accountId

-0.06

POSITIVE LOGITS

=en

0.07

 sqlite

0.06

Bài

0.06

具有

0.06

\Bundle

0.06

 traded

0.06

_RETRY

0.06

ivre

0.06

olecule

0.06

 vowels

0.05

Activations Density 0.011%

No Known Activations