INDEX

Explanations

function definitions

np_max-act · gemini-2.0-flash

The neuron detects Rust function definitions, i.e. occurrences of the `fn` keyword introducing a function.

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

�

-0.06

ρει

-0.06

AVING

-0.06

 Rhodes

-0.06

 Metrics

-0.06

ottesville

-0.06

ViewPager

-0.06

 recognized

-0.06

 vive

-0.06

唐

-0.06

POSITIVE LOGITS

.CustomButton

0.07

istro

0.07

 економ

0.07

。「

0.06

zoo

0.06

log

0.06

called

0.06

질

0.06

fun

0.06

 triplet

0.06

Activations Density 0.032%

function definitions

The neuron detects Rust function definitions, i.e. occurrences of the `fn` keyword introducing a function.

No Comments

No Known Activations