INDEX

Explanations

goal

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the word “goal,” i.e. when the text states the objective or purpose of something.

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

.userid

-0.07

 दल

-0.07

こそ

-0.06

 nostalg

-0.06

 XCTAssertEqual

-0.06

stateParams

-0.06

 reimburse

-0.06

 AccessToken

-0.06

 іс

-0.06

.DATE

-0.06

POSITIVE LOGITS

pn

0.07

ILA

0.07

τηκε

0.06

ừ

0.06

 disagrees

0.06

 Matchers

0.06

 erre

0.06

ıza

0.06

aktiv

0.06

prene

0.06

Activations Density 0.025%

goal

This neuron activates on occurrences of the word “goal,” i.e. when the text states the objective or purpose of something.

No Comments

No Known Activations

goal

This neuron activates on occurrences of the word “goal,” i.e. when the text states the objective or purpose of something.

No Comments

No Known Activations