INDEX

Explanations

mathematical formulas

np_max-act · gemini-2.0-flash

This neuron activates on numeric tokens—especially coefficients, constants, and intermediate numeric values—in mathematical expressions.

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

 Keller

-0.07

Nhap

-0.06

PathComponent

-0.06

:>

-0.06

(define

-0.06

llll

-0.06

'%

-0.06

 Barth

-0.06

/add

-0.06

路径

-0.06

POSITIVE LOGITS

 Vị

0.07

Container

0.07

Sheet

0.07

 dice

0.07

療

0.06

 excluded

0.06

 exclude

0.06

 payoff

0.06

ерж

0.06

měr

0.06

Activations Density 0.001%

mathematical formulas

This neuron activates on numeric tokens—especially coefficients, constants, and intermediate numeric values—in mathematical expressions.

No Comments

No Known Activations