INDEX

Explanations

phrases and structures related to personal experiences and opinions

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

ero

-0.17

aph

-0.17

-0.14

 idle

-0.14

antic

-0.14

acc

-0.14

ore

-0.13

-c

-0.13

go

-0.13

Ã¡

-0.13

POSITIVE LOGITS

 also

0.20

 ALSO

0.19

also

0.19

 takÃ©

0.18

Also

0.18

 ÑĤÐ°ÐºÐ¶Ðµ

0.17

 tambiÃ©n

0.16

 ÑĤÐ°ÐºÐ¾Ð¶

0.15

 tambÃ©m

0.15

 ëĺĲíķľ

0.15

Activations Density 0.418%

phrases and structures related to personal experiences and opinions

No Comments

No Known Activations