© 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 · 7-RESID-POST-AA · 33641 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
33641

INDEX

Explanations

period

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

Not in Any Lists

No Comments

Negative Logits

onald

-0.09

.k

-0.08

_STEP

-0.08

.a

-0.07

atsu

-0.07

美元

-0.07

-0.07

ANS

-0.07

at

-0.07

 GOLD

-0.07

POSITIVE LOGITS

 CLIIIK

0.06

	RETURN

0.06

Expression

0.05

زار

0.05

ThanOr

0.05

swagger

0.05

larınız

0.05

 Ferr

0.05

 anticipating

0.05

 Lazy

0.05

Activations Density 0.013%

No Known Activations