INDEX

Explanations

segments of code or export statements in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ovit

-0.16

 Public

-0.15

odb

-0.15

Pru

-0.15

ukkit

-0.15

odon

-0.15

cord

-0.14

.IContainer

-0.14

UDO

-0.14

Ã¡vÄĽ

-0.14

POSITIVE LOGITS

 export

0.57

export

0.54

 import

0.40

	export

0.40

 interface

0.38

interface

0.34

-export

0.33

.export

0.33

 Export

0.32

type

0.31

Activations Density 0.030%

segments of code or export statements in a programming context

No Comments

No Known Activations