INDEX

Explanations

nominations and awards

np_max-act · gemini-2.0-flash

The neuron detects mentions of awards and nominations (e.g. Emmys, Oscars, Golden Globes) and related context.

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

 Edition

-0.06

 прий

-0.06

_MARK

-0.06

ِب

-0.06

 Мон

-0.06

 Erot

-0.06

ビ

-0.06

 маль

-0.06

_SETTING

-0.06

 Gone

-0.06

POSITIVE LOGITS

 addr

0.07

configure

0.06

(withId

0.06

 سپ

0.06

Log

0.06

(components

0.06

 booth

0.06

![↵

0.06

log

0.06

NTAX

0.06

Activations Density 0.012%

nominations and awards

The neuron detects mentions of awards and nominations (e.g. Emmys, Oscars, Golden Globes) and related context.

No Comments

No Known Activations