INDEX

Explanations

code characters

np_max-act · gemini-2.0-flash

The neuron activates on decimal numeric literals (floating-point numbers) in code.

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

.tk

-0.07

prv

-0.07

应当

-0.07

kod

-0.07

TRAIN

-0.06

zde

-0.06

 treated

-0.06

 preparing

-0.06

 bald

-0.06

 第三

-0.06

POSITIVE LOGITS

={(

0.07

swagen

0.07

 війни

0.06

_FUN

0.06

	goto

0.06

	snprintf

0.06

 Gors

0.06

νο

0.06

 Гри

0.06

 Fiat

0.06

Activations Density 0.008%

code characters

The neuron activates on decimal numeric literals (floating-point numbers) in code.

No Comments

No Known Activations