INDEX

Explanations

quadratic

np_max-act · gemini-2.0-flash

The neuron activates on terms referring to quadratic equations (e.g. “kwadratowe” in Polish or English “quadratic,” “equation,” “quadratic formula”).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hiring

-0.06

(filepath

-0.06

Fat

-0.06

Ivy

-0.06

/></

-0.06

|_

-0.06

Jo

-0.06

Cancellation

-0.06

Pid

-0.06

 Minh

-0.06

POSITIVE LOGITS

ńst

0.07

writers

0.07

ersed

0.06

 مؤس

0.06

 dejting

0.06

 досвід

0.06

 henne

0.06

triangle

0.06

 Discrim

0.06

áky

0.06

Activations Density 0.013%

quadratic

The neuron activates on terms referring to quadratic equations (e.g. “kwadratowe” in Polish or English “quadratic,” “equation,” “quadratic formula”).

No Comments

No Known Activations