INDEX

Explanations

in

np_max-act · gemini-2.0-flash

This neuron detects the quantifier phrase “in a [number] of,” as in “in a number of ways.”

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

Cla

-0.07

 durable

-0.06

 presumed

-0.06

stood

-0.06

 slag

-0.06

OOSE

-0.06

();)

-0.06

 taş

-0.06

相当

-0.06

POSITIVE LOGITS

літ

0.07

.Chart

0.07

irq

0.07

programming

0.06

унк

0.06

istické

0.06

ológ

0.06

。不

0.06

_INFO

0.06

_AB

0.06

Activations Density 0.085%

in

This neuron detects the quantifier phrase “in a [number] of,” as in “in a number of ways.”

No Comments

No Known Activations