INDEX

Explanations

is

np_max-act · gemini-2.0-flash

The neuron fires on numeric tokens or numeric literals (digits and numbers) in the text.

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

%↵

-0.07

-flow

-0.06

ifornia

-0.06

EH

-0.06

Gem

-0.06

	dist

-0.06

_COMPLETED

-0.06

Analyzer

-0.06

(cors

-0.06

ětí

-0.06

POSITIVE LOGITS

 promotional

0.07

rootScope

0.06

 बर

0.06

:x

0.06

SWG

0.06

.de

0.06

.Serializable

0.06

bard

0.06

iali

0.06

cb

0.06

Activations Density 0.039%

is

The neuron fires on numeric tokens or numeric literals (digits and numbers) in the text.

No Comments

No Known Activations