INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron chiefly responds to floating-point numeric literals (i.e. tokens representing decimal numbers).

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.goto

-0.06

-finals

-0.06

 Zack

-0.06

CHEMY

-0.06

評

-0.06

stitial

-0.06

<object

-0.06

.longitude

-0.06

 Evans

-0.06

วด

-0.05

POSITIVE LOGITS

 státní

0.07

brands

0.07

 aggregator

0.06

propri

0.06

 mutate

0.06

로드

0.06

Cele

0.06

 target

0.06

 protections

0.06

Activations Density 0.004%

code

The neuron chiefly responds to floating-point numeric literals (i.e. tokens representing decimal numbers).

No Comments

No Known Activations