INDEX

Explanations

Number strings

np_max-act · gemini-2.0-flash

The neuron spots numeric tokens that include decimal points (i.e. floating‐point numbers).

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

-0.07

ií

-0.07

;:;:

-0.07

 raging

-0.06

 tài

-0.06

 pró

-0.06

νά

-0.06

 reservoir

-0.06

 гри

-0.06

POSITIVE LOGITS

 Closing

0.07

Copying

0.07

0.06

ovable

0.06

reported

0.06

 hydr

0.06

kinson

0.06

 Experiment

0.06

(coder

0.06

 extract

0.06

Activations Density 0.019%

Number strings

The neuron spots numeric tokens that include decimal points (i.e. floating‐point numbers).

No Comments

No Known Activations

Number strings

The neuron spots numeric tokens that include decimal points (i.e. floating‐point numbers).

No Comments

No Known Activations