INDEX

Explanations

comma

np_max-act · gemini-2.0-flash

The neuron is looking for floating‐point number tokens (i.e. decimal numeric literals).

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

-0.08

더

-0.07

 surf

-0.07

andal

-0.06

 surprises

-0.06

列

-0.06

otechnology

-0.06

충

-0.06

 trợ

-0.06

 anal

-0.06

POSITIVE LOGITS

 Peygamber

0.07

ísk

0.07

 newNode

0.06

 Xiao

0.06

 víde

0.06

ná

0.06

 performan

0.06

#ae

0.06

.yang

0.06

 backed

0.06

Activations Density 0.058%

comma

The neuron is looking for floating‐point number tokens (i.e. decimal numeric literals).

No Comments

No Known Activations