INDEX

Explanations

a

np_max-act · gemini-2.0-flash

This neuron detects instances of the indefinite article “a” introducing a person’s professional role or titled position.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rank

-0.07

.argv

-0.07

.Deserialize

-0.07

_news

-0.06

 方法

-0.06

productId

-0.06

 retrieval

-0.06

ICY

-0.06

 Investigators

-0.06

 menus

-0.06

POSITIVE LOGITS

같은

0.08

에

0.07

va

0.06

‌کن

0.06

 místa

0.06

가

0.06

 없었다

0.06

先生

0.06

 فاصله

0.06

Activations Density 0.020%

a

This neuron detects instances of the indefinite article “a” introducing a person’s professional role or titled position.

No Comments

No Known Activations