INDEX

Explanations

mathematical definitions and descriptions related to functions and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

arel

-0.17

ature

-0.16

ato

-0.15

dal

-0.15

atak

-0.14

hus

-0.14

stad

-0.14

çĿ£

-0.14

Ø§Ø¦ÙĬ

-0.14

isoft

-0.13

POSITIVE LOGITS

zelf

0.17

ÑĩÐµÑĢ

0.15

zych

0.14

Til

0.14

ãĥĥãĤ¯ãĤ¹

0.14

 Roose

0.13

again

0.13

 Incre

0.13

ì§ĳ

0.13

Activations Density 0.128%

mathematical definitions and descriptions related to functions and their properties

No Comments

No Known Activations