INDEX

Explanations

references to programming concepts and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

bh

-0.16

ëª»

-0.15

Ð¼Ð¿

-0.14

emento

-0.14

RegExp

-0.14

 CrossRef

-0.14

ë£Į

-0.14

 Ð·ÐµÐ¼Ð»Ð¸

-0.14

 FrantiÅ¡ek

-0.14

_DLL

-0.14

POSITIVE LOGITS

 nameof

0.20

 McCart

0.20

(nameof

0.18

 migrationBuilder

0.18

($"{

0.18

 cancellationToken

0.17

awa

0.17

Utf

0.17

 await

0.16

 CancellationToken

0.16

Activations Density 0.042%

references to programming concepts and methods

No Comments

No Known Activations