INDEX

Explanations

=

np_max-act · gemini-2.0-flash

The neuron fires on JavaScript code patterns that check for and reassign a callback when an argument (often named “options” or similar) is actually a function, e.g. `if (typeof options === "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

datable

-0.06

resenter

-0.06

LOGY

-0.06

.↵↵↵↵↵↵↵↵↵↵

-0.06

(size

-0.06

(Number

-0.06

頂

-0.05

 chains

-0.05

POSITIVE LOGITS

mpi

0.07

.getProduct

0.07

 мик

0.06

 dejting

0.06

 τρο

0.06

	Service

0.06

HttpGet

0.06

.entrySet

0.06

ミ

0.06

 بان

0.06

Activations Density 0.020%

=

The neuron fires on JavaScript code patterns that check for and reassign a callback when an argument (often named “options” or similar) is actually a function, e.g. `if (typeof options === "function") …`.

No Comments

No Known Activations

=

The neuron fires on JavaScript code patterns that check for and reassign a callback when an argument (often named “options” or similar) is actually a function, e.g. `if (typeof options === "function") …`.

No Comments

No Known Activations