INDEX

Explanations

references to specific years, particularly in the 1990s

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

isz

-0.15

ergy

-0.15

emo

-0.14

Ã¡lez

-0.14

eryl

-0.14

iets

-0.13

aydÄ±

-0.13

eral

-0.13

arp

-0.13

POSITIVE LOGITS

éĹ´

0.16

yonel

0.15

alog

0.15

istan

0.15

Roe

0.15

heim

0.14

ä¸»ä¹ī

0.14

-Za

0.14

avel

0.14

fel

0.14

Activations Density 0.033%

references to specific years, particularly in the 1990s

No Comments

No Known Activations