INDEX

Explanations

Track listings

np_max-act · gemini-2.0-flash

The neuron is looking for track time stamps or duration markers (minute:second formats) in the text.

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

_rates

-0.07

ektedir

-0.06

 commun

-0.06

 disastr

-0.06

 Guil

-0.06

κή

-0.06

imitive

-0.06

sexy

-0.06

owan

-0.06

uples

-0.05

POSITIVE LOGITS

 detention

0.07

MAY

0.07

.Ent

0.07

 imprisonment

0.06

,total

0.06

Measured

0.06

prot

0.06

 traveller

0.06

ีช

0.06

_IN

0.06

Activations Density 0.010%

Track listings

The neuron is looking for track time stamps or duration markers (minute:second formats) in the text.

No Comments

No Known Activations