INDEX

Explanations

are

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

Canon

-0.07

Math

-0.07

angement

-0.07

/************************************************************************

-0.06

 Inspector

-0.06

AMS

-0.06

Evidence

-0.06

_CNT

-0.06

altern

-0.06

.LastName

-0.06

POSITIVE LOGITS

竞

0.06

_text

0.06

柱

0.06

 heatmap

0.06

�

0.06

崇

0.06

.copyWith

0.06

烧

0.05

равиль

0.05

Activations Density 0.001%

are

No Comments

No Known Activations