INDEX

Explanations

Sentence boundaries

np_max-act · gemini-2.0-flash

This neuron is triggered by numeric measurement values, especially tokens containing decimal numbers.

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

ोट

-0.06

 обуч

-0.06

fontSize

-0.06

 Společ

-0.06

 Lambert

-0.06

 Additional

-0.06

غيل

-0.06

 Mann

-0.06

 criteria

-0.06

/INFO

-0.06

POSITIVE LOGITS

 devastated

0.07

 лікар

0.07

�

0.07

 appeals

0.06

 improves

0.06

jb

0.06

 Phân

0.06

vb

0.06

"?↵↵

0.06

 reversible

0.06

Activations Density 0.195%

Sentence boundaries

This neuron is triggered by numeric measurement values, especially tokens containing decimal numbers.

No Comments

No Known Activations