INDEX

Explanations

code

np_max-act · gemini-2.0-flash

programming-related terms and function definitions in code snippets.

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

The neuron activates on numeric literals—especially floating‐point constants—in source 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enso

-0.07

ıma

-0.06

 Россий

-0.06

 Clark

-0.06

oved

-0.06

áticas

-0.06

 hủy

-0.06

 Сов

-0.06

軟

-0.06

atan

-0.06

POSITIVE LOGITS

(handles

0.07

Nic

0.07

 forcefully

0.07

 altogether

0.06

Σ

0.06

 Contributor

0.06

Congress

0.06

 AVAILABLE

0.06

таб

0.06

 investigates

0.06

Activations Density 0.011%

code

programming-related terms and function definitions in code snippets.

The neuron activates on numeric literals—especially floating‐point constants—in source code.

No Comments

No Known Activations

code

programming-related terms and function definitions in code snippets.

The neuron activates on numeric literals—especially floating‐point constants—in source code.

No Comments

No Known Activations