© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 21441 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
21441

INDEX

Explanations

1

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

 medieval

-0.07

 blocks

-0.06

河

-0.06

 altered

-0.06

ipients

-0.06

yb

-0.06

 Tues

-0.06

 Spokane

-0.06

renders

-0.06

混合

-0.06

POSITIVE LOGITS

0.07

 bật

0.07

 skim

0.06

 appBar

0.06

Key

0.06

.El

0.06

Focused

0.06

成本

0.06

.additional

0.06

급

0.06

Activations Density 0.011%

No Known Activations