INDEX

Explanations

period

np_max-act · gemini-2.0-flash

This neuron responds to numeric tokens—especially decimal or floating‐point 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

oka

-0.06

('''

-0.06

Netflix

-0.06

otherwise

-0.06

 Thorn

-0.06

 inherits

-0.06

("

-0.06

irectory

-0.06

งข

-0.06

contracts

-0.06

POSITIVE LOGITS

xec

0.07

силь

0.07

-category

0.06

 Unsigned

0.06

 sunglasses

0.06

.psi

0.06

маз

0.06

 platí

0.06

.responseText

0.06

 chili

0.06

Activations Density 0.008%

period

This neuron responds to numeric tokens—especially decimal or floating‐point numbers—in the text.

No Comments

No Known Activations