INDEX

Explanations

programming-related terms and concepts 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 loadChildren

-0.16

recht

-0.15

ledo

-0.15

-transitional

-0.15

 nomine

-0.15

 èī

-0.14

_strerror

-0.14

æĺĮ

-0.14

ToFit

-0.14

ople

-0.14

POSITIVE LOGITS

 request

0.34

 Request

0.29

request

0.28

Request

0.27

(request

0.26

:request

0.26

 HttpServletRequest

0.26

 REQUEST

0.25

-request

0.25

.HttpServletRequest

0.23

Activations Density 0.107%

programming-related terms and concepts in code

No Comments

No Known Activations