INDEX

Explanations

runtime

np_max-act · gemini-2.0-flash

The neuron fires on tokens referring to the timing of type determination and code execution (e.g. “runtime,” “compile time,” “dynamic,” “execution”).

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

-fed

-0.07

しよう

-0.06

Merge

-0.06

 аналіз

-0.06

UILTIN

-0.06

 ucfirst

-0.06

사회

-0.06

 Angela

-0.06

.linspace

-0.06

 setzen

-0.06

POSITIVE LOGITS

 infiltration

0.07

esthetic

0.07

 aftermarket

0.06

 athletics

0.06

 disposition

0.06

 spend

0.06

ilitating

0.06

 Predator

0.06

 chóng

0.06

CSP

0.06

Activations Density 0.005%

runtime

The neuron fires on tokens referring to the timing of type determination and code execution (e.g. “runtime,” “compile time,” “dynamic,” “execution”).

No Comments

No Known Activations