INDEX

Explanations

programming references and code structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

zie

-0.14

utton

-0.14

ayo

-0.14

usi

-0.13

ui

-0.13

chn

-0.13

isphere

-0.13

STR

-0.13

 âĨĴ↵↵

-0.13

POSITIVE LOGITS

egers

0.15

æ§ĺ

0.14

llib

0.14

æ³Ĭ

0.13

istical

0.13

itaire

0.13

dra

0.13

istÃ©

0.13

cott

0.13

 opport

0.13

Activations Density 0.004%

programming references and code structures

No Comments

No Known Activations