INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

This neuron fires on decimal numeric literals (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

_pan

-0.06

SSION

-0.06

 embraces

-0.06

 precip

-0.06

 program

-0.06

onestly

-0.06

 STATUS

-0.06

AGIC

-0.06

(char

-0.06

Pacific

-0.06

POSITIVE LOGITS

基地

0.07

�

0.07

.offsetHeight

0.07

 Bangalore

0.06

 образования

0.06

AutoresizingMask

0.06

 στη

0.06

Queue

0.06

odable

0.06

 entitled

0.06

Activations Density 0.069%

Code

This neuron fires on decimal numeric literals (floating-point numbers) in the text.

No Comments

No Known Activations