INDEX

Explanations

definitely

np_max-act · gemini-2.0-flash

The neuron activates on the intensifying adverb “definitely.”

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

<r

-0.07

-power

-0.07

URNS

-0.07

 markers

-0.07

luent

-0.07

 cared

-0.06

ors

-0.06

<&

-0.06

our

-0.06

 walls

-0.06

POSITIVE LOGITS

 definitely

0.16

 Definitely

0.12

 dude

0.08

 definite

0.08

 Dude

0.07

 definit

0.07

ा:

0.07

 Gina

0.07

 určitě

0.07

chaft

0.07

Activations Density 0.008%

definitely

The neuron activates on the intensifying adverb “definitely.”

No Comments

No Known Activations