INDEX

Explanations

programming-related syntax and structure, particularly in relation to function calls and equality checks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

venes

-0.16

ugas

-0.16

oupon

-0.15

afort

-0.15

íĩ´

-0.15

Î¸Ïħ

-0.14

Cancelable

-0.14

ulus

-0.14

myModal

-0.14

redit

-0.14

POSITIVE LOGITS

adlo

0.15

keit

0.14

ne

0.14

-launch

0.14

 grav

0.14

launch

0.13

.serialize

0.13

IMIT

0.13

Wildcard

0.13

ges

0.13

Activations Density 0.003%

programming-related syntax and structure, particularly in relation to function calls and equality checks

No Comments

No Known Activations