INDEX

Explanations

in

np_max-act · gemini-2.0-flash

The neuron fires specifically on the floating-point year values (the decimal numbers) in the “described by … in YYYY” lines.

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

ZZ

-0.07

上传

-0.07

Branch

-0.06

isation

-0.06

Coder

-0.06

aktion

-0.06

 fragmentation

-0.06

OwnProperty

-0.06

QQ

-0.06

by

-0.06

POSITIVE LOGITS

 cancelButtonTitle

0.07

NDAR

0.07

put

0.07

 cómo

0.07

 Damen

0.07

age

0.06

<IActionResult

0.06

ових

0.06

(node

0.06

enzie

0.06

Activations Density 0.003%

in

The neuron fires specifically on the floating-point year values (the decimal numbers) in the “described by … in YYYY” lines.

No Comments

No Known Activations