INDEX

Explanations

annual events

np_max-act · gemini-2.0-flash

This neuron activates on temporal markers indicating years or anniversaries (e.g. “eighth year,” “annual,” “this year,” “every year”).

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

 trailing

-0.07

 configuring

-0.07

 контролю

-0.07

 infancy

-0.07

 Alone

-0.07

 Bang

-0.07

 Fruit

-0.07

 Sabbath

-0.07

-install

-0.07

 připrav

-0.07

POSITIVE LOGITS

targets

0.06

eken

0.06

，最

0.06

rec

0.06

菲

0.05

 Cler

0.05

แบ

0.05

۱۹۸

0.05

主義

0.05

집

0.05

Activations Density 0.067%

annual events

This neuron activates on temporal markers indicating years or anniversaries (e.g. “eighth year,” “annual,” “this year,” “every year”).

No Comments

No Known Activations