INDEX

Explanations

Code/configuration files

np_max-act · gemini-2.0-flash

The neuron consistently lights up on text that looks like Base64‐encoded data (e.g. the certificate contents in PEM blocks).

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

.Generated

-0.06

_RS

-0.06

سو

-0.06

ứ

-0.06

 basic

-0.06

_TB

-0.06

 Chen

-0.06

 tỏ

-0.06

UserCode

-0.06

 cooks

-0.06

POSITIVE LOGITS

근

0.07

*c

0.07

ISyntaxException

0.07

 Elegant

0.07

 palabra

0.07

단체

0.06

 مايو

0.06

['$

0.06

*r

0.06

ucked

0.06

Activations Density 0.069%

Code/configuration files

The neuron consistently lights up on text that looks like Base64‐encoded data (e.g. the certificate contents in PEM blocks).

No Comments

No Known Activations