INDEX

Explanations

Common English articles

np_max-act · gemini-2.0-flash

This neuron responds to general discourse/transition words (e.g. “about,” “discussion,” “destinations,” “always”) that introduce or frame topics.

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

.st

-0.08

 Bold

-0.07

escaping

-0.07

(div

-0.07

 Impress

-0.07

 plur

-0.06

Moves

-0.06

ottle

-0.06

	memcpy

-0.06

 Scrolls

-0.06

POSITIVE LOGITS

 захворю

0.07

 بهبود

0.07

 답변

0.06

 Caucasian

0.06

Projection

0.06

ジ

0.06

анта

0.06

 dịch

0.06

 الجن

0.06

 академ

0.06

Activations Density 0.000%

Common English articles

This neuron responds to general discourse/transition words (e.g. “about,” “discussion,” “destinations,” “always”) that introduce or frame topics.

No Comments

No Known Activations