INDEX

Explanations

instances of documentation and explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

caff

-0.15

Interop

-0.15

 yoksa

-0.15

 eiusmod

-0.14

anto

-0.13

Nug

-0.13

ANY

-0.13

ä»»ä½ķ

-0.13

ynet

-0.13

lian

-0.13

POSITIVE LOGITS

how

0.45

why

0.43

 briefly

0.35

how

0.32

why

0.30

 some

0.30

 ways

0.27

å¦Ĥä½ķ

0.26

 cÃ³mo

0.25

 reasons

0.25

Activations Density 0.168%

instances of documentation and explanations

No Comments

No Known Activations