INDEX

Explanations

periods

np_max-act · gemini-2.0-flash

The neuron spikes on comment‐block header lines that label or describe the file or module (e.g. “DESCRIPTION:”, “@file,” “brief,” or the “.cpp” filename line).

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

_PRESS

-0.06

plant

-0.06

irate

-0.06

	cache

-0.06

"]:

-0.06

 witnessed

-0.05

idia

-0.05

ارس

-0.05

 praying

-0.05

 Being

-0.05

POSITIVE LOGITS

 спад

0.08

Ste

0.07

 centerY

0.07

 başk

0.07

 Milli

0.06

...')↵

0.06

 طلا

0.06

Atoms

0.06

ความร

0.06

 Contributors

0.06

Activations Density 0.038%

periods

The neuron spikes on comment‐block header lines that label or describe the file or module (e.g. “DESCRIPTION:”, “@file,” “brief,” or the “.cpp” filename line).

No Comments

No Known Activations

periods

The neuron spikes on comment‐block header lines that label or describe the file or module (e.g. “DESCRIPTION:”, “@file,” “brief,” or the “.cpp” filename line).

No Comments

No Known Activations