© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 27921 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
27921

INDEX

Explanations

punctuation

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

child

-0.07

.plus

-0.06

dığını

-0.06

 fins

-0.06

zat

-0.06

_mix

-0.06

	bytes

-0.06

_cc

-0.06

Jag

-0.05

.ContainsKey

-0.05

POSITIVE LOGITS

컴

0.08

 counter

0.06

CP

0.06

 нем

0.06

 neutr

0.06

 Interpreter

0.06

 enzym

0.06

 Genetic

0.06

 Instrument

0.06

 ####

0.06

Activations Density 0.013%

No Known Activations