INDEX

Explanations

.

np_max-act · gemini-2.0-flash

The neuron is tuned to detect numeric tokens—digits and numbers (e.g. dates, counts, percentages, durations) wherever they appear in the text.

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

Cbd

-0.08

увався

-0.07

/******/↵

-0.07

pter

-0.06

emain

-0.06

spawn

-0.06

'n

-0.06

 GitHub

-0.06

-mean

-0.06

 }),↵↵

-0.06

POSITIVE LOGITS

asset

0.06

 subtotal

0.06

 affordability

0.06

 SUCH

0.06

 enlightenment

0.06

owo

0.06

ocus

0.06

 Сан

0.06

=<?

0.05

 deciding

0.05

Activations Density 0.069%

.

The neuron is tuned to detect numeric tokens—digits and numbers (e.g. dates, counts, percentages, durations) wherever they appear in the text.

No Comments

No Known Activations