INDEX

Explanations

phrases related to guidance, support, and ensuring quality experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 remainder

-0.16

mir

-0.15

lias

-0.14

 part

-0.13

ilar

-0.13

 rarely

-0.13

 almost

-0.13

 instant

-0.13

ob

-0.13

 stop

-0.13

POSITIVE LOGITS

 maximum

0.43

 maximal

0.42

æľĢä½³

0.41

maximum

0.39

æľĢå¤§

0.38

 optimum

0.37

 best

0.36

 optimal

0.36

 mÃ¡ximo

0.35

best

0.35

Activations Density 0.380%

phrases related to guidance, support, and ensuring quality experiences

No Comments

No Known Activations