INDEX

Explanations

To

np_max-act · gemini-2.0-flash

This neuron specifically activates on the infinitive marker “to” in English (as used in instructions or directives).

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

 oceans

-0.07

 Picture

-0.06

.gif

-0.06

 erupted

-0.06

laden

-0.06

喊

-0.06

 readonly

-0.06

 vect

-0.06

 array

-0.06

 residents

-0.06

POSITIVE LOGITS

 acknowled

0.07

τας

0.06

.GroupLayout

0.06

 HVAC

0.06

 Wealth

0.06

uti

0.06

 Дата

0.06

 attempts

0.06

 существ

0.06

한테

0.06

Activations Density 0.003%

To

This neuron specifically activates on the infinitive marker “to” in English (as used in instructions or directives).

No Comments

No Known Activations