INDEX

Explanations

Technical/scientific writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.Restr

-0.07

Gus

-0.06

&q

-0.06

fcn

-0.06

.post

-0.06

，却

-0.06

.mob

-0.06

.mark

-0.06

ubuntu

-0.06

ikal

-0.06

POSITIVE LOGITS

ר

0.07

,*

0.07

 sonrasında

0.06

 Landscape

0.06

 trajectory

0.06

 optimize

0.06

-value

0.06

 Tillerson

0.06

Candidates

0.06

Activations Density 0.000%

Technical/scientific writing

No Comments

No Known Activations