INDEX

Explanations

Code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 classroom

-0.07

 annoy

-0.07

 Greece

-0.07

 Німеч

-0.06

 defendant

-0.06

 искус

-0.06

 lesen

-0.06

 justify

-0.06

 pravidel

-0.06

###############################################################################↵

-0.06

POSITIVE LOGITS

PerPixel

0.07

/*------------------------------------------------

0.06

²

0.06

 AssemblyCompany

0.06

 мог

0.06

CALE

0.06

elier

0.06

 ImageIcon

0.06

_EXTENSION

0.06

(ViewGroup

0.06

Activations Density 0.019%

Code snippets

No Comments

No Known Activations

Code snippets

No Comments

No Known Activations