INDEX

Explanations

programming terminology and functions related to handling attributes and executing queries in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ajor

-0.16

Sar

-0.15

[o

-0.14

idor

-0.13

lyn

-0.13

nest

-0.13

 Covered

-0.13

è¼Ķ

-0.13

own

-0.13

.SimpleButton

-0.12

POSITIVE LOGITS

è¦ģ

0.18

akens

0.15

zin

0.15

 whom

0.15

APT

0.14

 dahil

0.14

whose

0.14

ìĿ´ìŀĲ

0.14

 cÃ©lib

0.14

 desired

0.14

Activations Density 0.019%

programming terminology and functions related to handling attributes and executing queries in code

No Comments

No Known Activations