INDEX

Explanations

demographics

np_max-act · gemini-2.0-flash

This neuron does not activate on any of the input tokens and thus appears to be entirely inactive (i.e. it finds nothing).

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

Negative Logits

dict

-0.07

onn

-0.07

 fres

-0.06

	last

-0.06

ま

-0.06

lán

-0.06

ματα

-0.06

meta

-0.06

ropol

-0.06

 موس

-0.06

POSITIVE LOGITS

Watching

0.07

.Contact

0.06

 중요한

0.06

 Sın

0.06

‌

0.06

[keys

0.06

ıs

0.06

 constrained

0.06

 conventional

0.06

 Transcript

0.06

Activations Density 0.000%

demographics

This neuron does not activate on any of the input tokens and thus appears to be entirely inactive (i.e. it finds nothing).

No Known Activations