INDEX

Explanations

in

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens representing decimal values (e.g. measurements, confidence‐intervals, p‐values).

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

Rank

-0.07

 Addresses

-0.06

 vocalist

-0.06

 records

-0.06

そこ

-0.06

 Chapters

-0.06

ilater

-0.06

 endeavors

-0.06

EST

-0.06

 ánh

-0.06

POSITIVE LOGITS

0.06

 густ

0.06

linik

0.06

hapus

0.06

 Panel

0.06

.rmi

0.06

MPI

0.06

 demolished

0.06

 Devon

0.06

()")↵

0.06

Activations Density 0.018%

in

The neuron activates on numeric tokens representing decimal values (e.g. measurements, confidence‐intervals, p‐values).

No Comments

No Known Activations