© 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 · 7-RESID-POST-AA · 57057 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
57057

INDEX

Explanations

severe

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

 нанес

-0.07

Weekly

-0.07

 decrement

-0.07

 shrugged

-0.07

.curr

-0.07

FOR

-0.06

inski

-0.06

zus

-0.06

 Assigned

-0.06

 ngày

-0.06

POSITIVE LOGITS

 severe

0.08

된다

0.06

 INTERRUPTION

0.06

 тяж

0.06

.non

0.06

 보내

0.06

 precisely

0.06

 γε

0.06

_value

0.06

可

0.06

Activations Density 0.008%

No Known Activations