INDEX

Explanations

most

np_max-act · gemini-2.0-flash

The neuron activates on superlative and emphatic positive descriptors (e.g. “most,” “popular,” “successful,” “influential,” “beloved”).

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

ूल

-0.07

 silver

-0.07

 kní

-0.06

터

-0.06

	category

-0.06

 Dialogue

-0.06

CFL

-0.06

乾

-0.06

(Date

-0.06

 Fakat

-0.06

POSITIVE LOGITS

 most

0.08

emplates

0.08

 Most

0.08

 //----------------------------------------------------------------

0.07

 post

0.07

 assuming

0.07

	model

0.07

ToShow

0.07

 enact

0.07

instr

0.06

Activations Density 0.022%

most

The neuron activates on superlative and emphatic positive descriptors (e.g. “most,” “popular,” “successful,” “influential,” “beloved”).

No Comments

No Known Activations