INDEX

Explanations

programming-related terms and functions in the context of coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ä¼ģ

-0.15

.fp

-0.15

ÃŃnÄĽ

-0.14

oggler

-0.14

/on

-0.14

 çİ

-0.14

 coll

-0.13

Ãºmer

-0.13

osi

-0.13

trusted

-0.13

POSITIVE LOGITS

egasus

0.15

Wan

0.14

 CHIP

0.14

urch

0.14

 Alman

0.14

 Spoon

0.13

 Wass

0.13

 MILF

0.13

agrid

0.13

 Gratuit

0.13

Activations Density 0.119%

programming-related terms and functions in the context of coding

No Comments

No Known Activations