INDEX

Explanations

Programming code

np_max-act · gemini-2.0-flash

technical terms and code-related expressions in the context of programming.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

This neuron activates on words in code documentation comments—especially terms describing how methods send or emit “elements” or events to an “observer” (e.g. “sends,” “elements,” “observer,” “events,” “returns,” “parameter”).

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

overy

-0.07

 spat

-0.07

 refused

-0.07

 Cron

-0.06

 rapes

-0.06

Bern

-0.06

Brun

-0.06

ologie

-0.06

kam

-0.06

 userDetails

-0.06

POSITIVE LOGITS

(correct

0.07

 cmdline

0.07

administrator

0.06

pizza

0.06

 ConfigurationManager

0.06

dhcp

0.06

收益

0.06

ести

0.06

 الدر

0.06

adoop

0.06

Activations Density 0.024%

Programming code

technical terms and code-related expressions in the context of programming.

This neuron activates on words in code documentation comments—especially terms describing how methods send or emit “elements” or events to an “observer” (e.g. “sends,” “elements,” “observer,” “events,” “returns,” “parameter”).

No Comments

No Known Activations

Programming code

technical terms and code-related expressions in the context of programming.

This neuron activates on words in code documentation comments—especially terms describing how methods send or emit “elements” or events to an “observer” (e.g. “sends,” “elements,” “observer,” “events,” “returns,” “parameter”).

No Comments

No Known Activations