INDEX

Explanations

(!

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of the logical‐NOT operator (`!`), especially in `if (!…)` style checks.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

function definitions and their corresponding parameters within code snippets.

oai_token-act-pair · gpt-4o-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

Hud

-0.07

 motivated

-0.07

组

-0.07

marca

-0.07

샤

-0.06

Telefone

-0.06

 sieve

-0.06

domain

-0.06

 detalle

-0.06

 shovel

-0.06

POSITIVE LOGITS

 fake

0.07

iky

0.06

 nebyl

0.06

itial

0.06

ABA

0.06

_NO

0.06

unist

0.06

atoire

0.06

nar

0.06

子供

0.06

Activations Density 0.004%

(!

The neuron fires on occurrences of the logical‐NOT operator (`!`), especially in `if (!…)` style checks.

function definitions and their corresponding parameters within code snippets.

No Comments

No Known Activations

(!

The neuron fires on occurrences of the logical‐NOT operator (`!`), especially in `if (!…)` style checks.

function definitions and their corresponding parameters within code snippets.

No Comments

No Known Activations