INDEX

Explanations

references to technology and legislative issues

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

Ð½Ð´

-0.16

ovaly

-0.16

/cop

-0.16

ylland

-0.15

 Balance

-0.15

 Dispatch

-0.14

onse

-0.14

à¸§à¸¥

-0.14

Ð³Ð»ÑıÐ´

-0.14

ikip

-0.14

POSITIVE LOGITS

war

0.21

War

0.20

0.18

war

0.18

_war

0.17

ban

0.17

Mor

0.17

-war

0.16

War

0.16

allen

0.16

Activations Density 0.005%

references to technology and legislative issues

No Comments

No Known Activations