INDEX

Explanations

phrases and sentences that express curiosity or pose questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

avin

-0.18

ooke

-0.17

erguson

-0.15

áº£ng

-0.15

uder

-0.15

ÎµÏį

-0.14

 TCHAR

-0.14

canf

-0.14

oplayer

-0.14

<source

-0.13

POSITIVE LOGITS

ati

0.15

 BALL

0.14

afia

0.14

abr

0.14

ara

0.14

 Ball

0.14

arra

0.14

ENA

0.13

 combust

0.13

ska

0.13

Activations Density 0.017%

phrases and sentences that express curiosity or pose questions

No Comments

No Known Activations