INDEX

Explanations

use

np_max-act · gemini-2.0-flash

The neuron responds to numeric tokens, especially floating-point numbers (decimal values).

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

hen

-0.08

 toss

-0.07

 masters

-0.07

-as

-0.07

 Density

-0.07

 encouraging

-0.06

 mixing

-0.06

 корот

-0.06

udios

-0.06

 refusing

-0.06

POSITIVE LOGITS

_notice

0.06

 EVERY

0.06

 выбор

0.06

 extremist

0.06

',...↵

0.06

/power

0.06

ApiResponse

0.06

 currentValue

0.06

……。

0.06

_WIFI

0.06

Activations Density 0.016%

use

The neuron responds to numeric tokens, especially floating-point numbers (decimal values).

No Comments

No Known Activations