INDEX

Explanations

of

np_max-act · gemini-2.0-flash

The neuron activates on the word “type” (and its equivalents, like “tipo” or “de … ”) when it appears in phrases asking “what type of … ” or “qual o tipo de … .”

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

 monopol

-0.06

.WebElement

-0.06

ITES

-0.06

Uno

-0.06

 produ

-0.06

 blackmail

-0.05

이슈

-0.05

ौर

-0.05

twitter

-0.05

PositiveButton

-0.05

POSITIVE LOGITS

 Even

0.07

	assertThat

0.07

 super

0.07

}_${

0.07

 Institutions

0.06

请

0.06

移到

0.06

 Modifications

0.06

recognized

0.06

ava

0.06

Activations Density 0.011%

of

The neuron activates on the word “type” (and its equivalents, like “tipo” or “de … ”) when it appears in phrases asking “what type of … ” or “qual o tipo de … .”

No Comments

No Known Activations

of

The neuron activates on the word “type” (and its equivalents, like “tipo” or “de … ”) when it appears in phrases asking “what type of … ” or “qual o tipo de … .”

No Comments

No Known Activations