INDEX

Explanations

programming constructs and syntax used in coding

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

otta

-0.14

å±±å¸Ĥ

-0.14

imple

-0.14

lav

-0.14

Ñİ

-0.13

å·ŀå¸Ĥ

-0.13

 tiled

-0.13

Ð¸ÑģÐ»Ð¾Ð²

-0.12

åıĸãĤĬ

-0.12

Ã£

-0.12

POSITIVE LOGITS

Î¼Î¼

0.16

emek

0.16

åĤ

0.15

istrovstvÃŃ

0.15

axies

0.14

xico

0.14

alama

0.13

ammo

0.13

ç´Ģ

0.13

-none

0.13

Activations Density 0.330%

programming constructs and syntax used in coding

No Comments

No Known Activations