INDEX

Explanations

code-related terms and parameters associated with data processing and event handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

GuidId

-0.19

HeaderCode

-0.16

 glGen

-0.16

RuntimeObject

-0.15

URLException

-0.14

_icall

-0.13

SupportedContent

-0.13

UrlParser

-0.13

CppClass

-0.13

_TypeInfo

-0.12

POSITIVE LOGITS

Multiplier

0.30

Factor

0.28

Percentage

0.27

Ratio

0.27

Percent

0.26

_factor

0.25

 Factor

0.25

Threshold

0.25

factor

0.25

 float

0.24

Activations Density 0.254%

code-related terms and parameters associated with data processing and event handling

No Comments

No Known Activations