INDEX

Explanations

merit

np_max-act · gemini-2.0-flash

The neuron detects phrases in judicial opinions that assert an issue “lacks merit” or has “not been shown,” i.e. expressions stating that an appeal or argument is without merit.

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

<G

-0.07

,:,

-0.06

 eskort

-0.06

 wears

-0.06

 venture

-0.06

と思う

-0.06

 मश

-0.06

aires

-0.06

 вигля

-0.06

eç

-0.06

POSITIVE LOGITS

Markdown

0.07

omite

0.07

ContentView

0.07

 Pride

0.06

 glove

0.06

 frække

0.06

 jadx

0.06

_ITEM

0.06

DrawerToggle

0.06

Facebook

0.06

Activations Density 0.004%

merit

The neuron detects phrases in judicial opinions that assert an issue “lacks merit” or has “not been shown,” i.e. expressions stating that an appeal or argument is without merit.

No Comments

No Known Activations