INDEX

Explanations

multicast

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the term “multicast” (i.e. references to multicast networking transmissions).

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

Berlin

-0.07

ादन

-0.06

 она

-0.06

.hits

-0.06

金

-0.06

 dramas

-0.06

 Workers

-0.06

Samples

-0.06

δά

-0.06

fn

-0.06

POSITIVE LOGITS

 multicast

0.08

Copying

0.07

 حسب

0.07

|>

0.07

HOST

0.06

 Hudson

0.06

icast

0.06

 nest

0.06

.BackgroundColor

0.06

asting

0.06

Activations Density 0.002%

multicast

The neuron activates on occurrences of the term “multicast” (i.e. references to multicast networking transmissions).

No Comments

No Known Activations