INDEX

Explanations

artificial intelligence

np_max-act · gemini-2.0-flash

The neuron flags mentions of generative‐AI concepts and content‐generation terms (e.g. “generative AI,” “AI,” “create,” “generate,” “content,” “videos,” etc.).

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

tn

-0.07

pyl

-0.07

 Bitte

-0.06

をか

-0.06

ání

-0.06

 administer

-0.06

xEE

-0.06

.GetLength

-0.06

 принадлеж

-0.06

FilterWhere

-0.06

POSITIVE LOGITS

 listView

0.07

."\

0.06

들의

0.06

/date

0.06

 h�

0.06

 гре

0.06

 nghe

0.06

 trademark

0.06

 profes

0.06

Activations Density 0.026%

artificial intelligence

The neuron flags mentions of generative‐AI concepts and content‐generation terms (e.g. “generative AI,” “AI,” “create,” “generate,” “content,” “videos,” etc.).

No Comments

No Known Activations