INDEX

Explanations

Runtime

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the identifier “Runtime” in code or metadata references.

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

�

-0.07

 ancestor

-0.07

 сиг

-0.07

acc

-0.06

 Beach

-0.06

 serv

-0.06

osed

-0.06

_CL

-0.06

 show

-0.06

 cover

-0.06

POSITIVE LOGITS

runtime

0.11

 Runtime

0.11

Runtime

0.11

	Runtime

0.10

 runtime

0.10

.Runtime

0.09

.runtime

0.09

 dateTime

0.09

 lstm

0.09

/Runtime

0.09

Activations Density 0.005%

Runtime

This neuron activates on occurrences of the identifier “Runtime” in code or metadata references.

No Comments

No Known Activations