INDEX

Explanations

subconscious mind

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

 Invite

-0.07

 Directorate

-0.06

hů

-0.06

 flashy

-0.06

 elimination

-0.06

 Madagascar

-0.06

خاص

-0.06

 Elim

-0.06

soo

-0.06

�

-0.06

POSITIVE LOGITS

 Transcript

0.07

 desperate

0.07

cloud

0.07

Cloud

0.07

 searchBar

0.06

MARK

0.06

quiv

0.06

-desc

0.06

.arch

0.06

 tacos

0.06

Activations Density 0.111%

subconscious mind

No Comments

No Known Activations