INDEX

Explanations

a, an

np_max-act · gemini-2.0-flash

The neuron detects indefinite articles (“a” or “an”) introducing descriptive appositive phrases that define or characterize a term.

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

ihar

-0.07

atório

-0.07

.Api

-0.06

 korun

-0.06

GameState

-0.06

Liked

-0.06

 striped

-0.06

 enthusi

-0.06

ครง

-0.06

-devel

-0.06

POSITIVE LOGITS

 nearing

0.08

coordinate

0.07

icha

0.06

:Object

0.06

шим

0.06

ah

0.06

isl

0.06

 endorsing

0.06

lical

0.06

(numpy

0.06

Activations Density 0.027%

a, an

The neuron detects indefinite articles (“a” or “an”) introducing descriptive appositive phrases that define or characterize a term.

No Comments

No Known Activations