INDEX

Explanations

select

np_max-act · gemini-2.0-flash

The neuron activates on words or word fragments that mean “selection” or “choosing.”

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

 İmparator

-0.07

	JPanel

-0.06

lbl

-0.06

com

-0.06

راق

-0.06

box

-0.06

.ReadFile

-0.06

 розповід

-0.06

	alert

-0.05

feito

-0.05

POSITIVE LOGITS

 selecting

0.10

 chose

0.09

 selected

0.09

 Choosing

0.09

 choose

0.09

 choosing

0.09

 Picks

0.08

 picks

0.07

Choosing

0.07

 pick

0.07

Activations Density 0.040%

select

The neuron activates on words or word fragments that mean “selection” or “choosing.”

No Comments

No Known Activations