© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 45481 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
45481

INDEX

Explanations

territory

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

嘴

-0.07

zx

-0.07

塑

-0.06

—from

-0.06

 assurance

-0.06

_beta

-0.06

سبب

-0.06

azo

-0.06

.AutoField

-0.06

%"

-0.06

POSITIVE LOGITS

 лі

0.07

STE

0.06

 longitud

0.06

 mCurrent

0.06

Susp

0.06

(PyObject

0.06

個

0.06

 mannen

0.06

 reserv

0.06

 наших

0.06

Activations Density 0.004%

No Known Activations