INDEX

Explanations

Math

np_max-act · gemini-2.0-flash

This neuron detects LaTeX mathematical superscripts and related subscript/exponent notation in formulas.

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

氏

-0.07

corner

-0.07

 primo

-0.07

\Configuration

-0.06

ाइम

-0.06

 خاص

-0.06

ields

-0.06

zda

-0.06

(Field

-0.06

_modified

-0.06

POSITIVE LOGITS

 Material

0.07

_picture

0.07

egrity

0.06

accum

0.06

 Нат

0.06

となった

0.06

Cause

0.06

 رج

0.06

.Predicate

0.06

Gab

0.06

Activations Density 0.005%

Math

This neuron detects LaTeX mathematical superscripts and related subscript/exponent notation in formulas.

No Comments

No Known Activations