INDEX

Explanations

said

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens—especially decimal numbers, percentages, and monetary figures.

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

алеж

-0.06

альная

-0.06

 انج

-0.06

-president

-0.06

FAULT

-0.06

 "")
↵

-0.06

isans

-0.06

_AGENT

-0.06

 questo

-0.06

POSITIVE LOGITS

 coinc

0.07

 witches

0.07

_hor

0.06

 SharedModule

0.06

_gt

0.06

Crime

0.06

鸡

0.06

 prakt

0.06

Yol

0.06

(rand

0.06

Activations Density 0.064%

said

The neuron activates on numeric tokens—especially decimal numbers, percentages, and monetary figures.

No Comments

No Known Activations