INDEX

Explanations

references to awards and achievements in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

gorm

-0.18

 McMahon

-0.17

eger

-0.15

ifo

-0.14

issing

-0.14

/navigation

-0.14

anta

-0.14

abcd

-0.13

 Magnus

-0.13

POSITIVE LOGITS

lc

0.14

 ÙĪØ§ÙĦØ¯

0.14

 ëĦ¤ìĿ´íĬ¸

0.14

ÎµÎ½Î¿

0.13

è½

0.13

.libs

0.13

 ÎłÎ±

0.13

 Dayton

0.13

hom

0.13

vla

0.13

Activations Density 0.057%

references to awards and achievements in various fields

No Comments

No Known Activations