© 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 · 11-RESID-POST-AA · 101299 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
101299

INDEX

Explanations

hazards

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

Negative Logits

.peek

-0.07

dir

-0.07

 Sussex

-0.06

olor

-0.06

 plav

-0.06

uyo

-0.06

ictionary

-0.06

?!↵↵

-0.06

 corps

-0.06

fwrite

-0.06

POSITIVE LOGITS

AL

0.07

_AL

0.06

(ARG

0.06

 Mezi

0.06

-existing

0.06

0.06

曼

0.06

Penn

0.06

.da

0.06

 bitmask

0.06

Activations Density 0.065%

No Known Activations