INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens—especially floating-point values—used to convey quantitative metrics and statistics.

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

İSİ

-0.07

versions

-0.06

ypse

-0.06

αλ

-0.06

.so

-0.06

�

-0.06

uv

-0.06

_INVALID

-0.06

retrieve

-0.06

 Extreme

-0.06

POSITIVE LOGITS

cca

0.07

 Estr

0.06

(LL

0.06

 fermentation

0.06

 influences

0.06

kol

0.06

 verr

0.06

 مرة

0.06

 reciprocal

0.06

Kw

0.06

Activations Density 0.042%

numbers

The neuron activates on numeric tokens—especially floating-point values—used to convey quantitative metrics and statistics.

No Comments

No Known Activations

numbers

The neuron activates on numeric tokens—especially floating-point values—used to convey quantitative metrics and statistics.

No Comments

No Known Activations