INDEX

Explanations

around/round

np_max-act · gemini-2.0-flash

The neuron activates on tokens that are parts of decimal numbers (i.e. numeric tokens containing a dot and digits).

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

 COLOR

-0.06

 below

-0.06

 recieved

-0.06

 threshold

-0.06

telegram

-0.06

-buffer

-0.06

 openFileDialog

-0.06

 connectors

-0.06

 dét

-0.06

%(

-0.06

POSITIVE LOGITS

лу

0.08

 bán

0.07

旁

0.07

ROC

0.06

 üretim

0.06

 olmak

0.06

 simulated

0.06

UIView

0.06

 impass

0.06

Inicio

0.06

Activations Density 0.015%

around/round

The neuron activates on tokens that are parts of decimal numbers (i.e. numeric tokens containing a dot and digits).

No Comments

No Known Activations

around/round

The neuron activates on tokens that are parts of decimal numbers (i.e. numeric tokens containing a dot and digits).

No Comments

No Known Activations