INDEX

Explanations

technical terms related to programming and data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 ÄĳÃ£

-0.25

 telah

-0.24

 à¤īà¤¸à¤¨

-0.23

 Äĳang

-0.21

 recently

-0.21

 hadn

-0.20

å·²ç»ı

-0.20

å·²

-0.19

 haven

-0.19

recent

-0.19

POSITIVE LOGITS

 becomes

0.40

 gets

0.32

 become

0.32

 blir

0.27

 comes

0.26

 olur

0.26

bec

0.25

 goes

0.25

 wird

0.24

ãģ¨ãģªãĤĭ

0.24

Activations Density 0.521%

technical terms related to programming and data management

No Comments

No Known Activations