INDEX

Explanations

max, range

np_max-act · gemini-2.0-flash

The neuron fires on numeric literals that include a decimal point (i.e. floating-point 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

Issues

-0.07

 devoid

-0.07

Nu

-0.06

 نظ

-0.06

šit

-0.06

Greg

-0.06

 SQUARE

-0.06

 COMPUT

-0.06

 nuôi

-0.06

 Subcommittee

-0.06

POSITIVE LOGITS

 mAdapter

0.07

 Hait

0.07

对象

0.07

ropping

0.07

 precipitation

0.07

負

0.06

 hãng

0.06

	exit

0.06

 도시

0.06

 edil

0.06

Activations Density 0.029%

max, range

The neuron fires on numeric literals that include a decimal point (i.e. floating-point numbers).

No Comments

No Known Activations