INDEX

Explanations

references to exchanges or transactions between parties

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

Negative Logits

li

-0.16

fil

-0.15

amate

-0.14

atement

-0.14

aceae

-0.14

dÃŃ

-0.14

ledon

-0.14

transparent

-0.14

 Ø¨ÛĮØ±

-0.14

xD

-0.14

POSITIVE LOGITS

frau

0.18

exchange

0.17

 exchange

0.15

iesen

0.15

 Ð¼ÐµÐ¶Ð´Ñĥ

0.15

 Ð¼ÑĸÐ¶

0.15

istrovstvÃŃ

0.15

 Äĳá»ķi

0.15

anter

0.15

 between

0.14

Activations Density 0.030%

references to exchanges or transactions between parties

No Known Activations