INDEX

Explanations

random topics

np_max-act · gemini-2.0-flash

The neuron is detecting mentions of “humor negro” (dark/black humor) requests.

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

ES

-0.07

지요

-0.07

Yug

-0.07

 safe

-0.07

 Bread

-0.06

EK

-0.06

EK

-0.06

Had

-0.06

 Sunder

-0.06

_LVL

-0.06

POSITIVE LOGITS

 đàn

0.06

-half

0.06

 numbers

0.06

ournal

0.06

ago

0.06

elry

0.06

Sweden

0.06

 helf

0.06

 regexp

0.06

 slova

0.06

Activations Density 0.356%

random topics

The neuron is detecting mentions of “humor negro” (dark/black humor) requests.

No Comments

No Known Activations