INDEX

Explanations

ion

np_max-act · gemini-2.0-flash

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

.Package

-0.07

	glog

-0.07

 Maryland

-0.06

xfb

-0.06

 breakfast

-0.06

“All

-0.06

 calc

-0.06

POSITIVE LOGITS

 Tiger

0.12

 Lions

0.12

 Lion

0.11

 lions

0.11

 tiger

0.10

 lion

0.10

Leo

0.09

优

0.08

ion

0.08

 Tigers

0.07

Activations Density 0.006%

ion

No Comments

No Known Activations