INDEX

Explanations

specific applications

np_max-act · gemini-2.0-flash

This neuron detects words and phrases that discuss what something is suited for or depends on—i.e. mentions of applications, tasks, or specific use-cases.

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

짓

-0.06

 transplant

-0.06

distance

-0.06

nak

-0.06

 ticaret

-0.06

 filepath

-0.06

_confirm

-0.06

_From

-0.06

POSITIVE LOGITS

	assert

0.07

 usually

0.07

原

0.06

 відріз

0.06

shi

0.06

.Equals

0.06

松

0.06

len

0.06

 Pair

0.06

�

0.06

Activations Density 0.041%

specific applications

This neuron detects words and phrases that discuss what something is suited for or depends on—i.e. mentions of applications, tasks, or specific use-cases.

No Comments

No Known Activations