INDEX

Explanations

warnings, dangers

np_max-act · gemini-2.0-flash

This neuron activates on promotional or evaluative adjectives and superlative descriptors in product or marketing language.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[y

-0.07

_tot

-0.07

економ

-0.07

ơ

-0.07

 resizeMode

-0.07

 Scre

-0.07

-using

-0.06

(m

-0.06

uish

-0.06

 กร

-0.06

POSITIVE LOGITS

 HACK

0.06

_AUDIO

0.06

 Iranian

0.06

LabelText

0.06

.pat

0.06

Att

0.06

↵

0.06

-associated

0.06

 руб

0.06

\Modules

0.06

Activations Density 0.569%

warnings, dangers

This neuron activates on promotional or evaluative adjectives and superlative descriptors in product or marketing language.

No Comments

No Known Activations