INDEX

Explanations

Account creation

np_max-act · gemini-2.0-flash

The neuron detects instructional or procedural language, especially second-person (“you”) directives and step-by-step guidance.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 game

-0.07

 mocking

-0.07

模型

-0.06

èo

-0.06

 Property

-0.06

显

-0.06

 Game

-0.06

 valido

-0.06

PDF

-0.06

_offset

-0.06

POSITIVE LOGITS

(!(

0.08

 στρα

0.06

秦

0.06

odied

0.06

 наблю

0.06

zev

0.06

 subdiv

0.06

 sağlıklı

0.06

mouseout

0.06

�

0.06

Activations Density 0.052%

Account creation

The neuron detects instructional or procedural language, especially second-person (“you”) directives and step-by-step guidance.

No Comments

No Known Activations