INDEX

Explanations

references to books or written materials

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 crow

-0.17

wner

-0.16

htub

-0.14

 Crow

-0.14

Ãºsqueda

-0.14

èħ¹

-0.14

Crow

-0.14

iser

-0.14

crow

-0.13

 cogn

-0.13

POSITIVE LOGITS

elian

0.15

afone

0.15

erce

0.14

Ã¨o

0.14

lio

0.14

ledo

0.14

arp

0.13

xic

0.13

arent

0.13

LI

0.13

Activations Density 0.024%

references to books or written materials

No Comments

No Known Activations