INDEX

Explanations

hypnosis

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

几乎

-0.07

 Ethernet

-0.07

новид

-0.06

Newton

-0.06

 movements

-0.06

Hun

-0.06

손

-0.06

 posts

-0.06

 ребенок

-0.06

.yellow

-0.06

POSITIVE LOGITS

textView

0.07

	cell

0.07

 ^{↵

0.06

 Collect

0.06

 Written

0.06

.Filters

0.06

 rewritten

0.06

[:,

0.06

.delegate

0.06

anlar

0.06

Activations Density 0.021%

hypnosis

No Comments

No Known Activations