INDEX

Explanations

statements and propositions related to potential issues 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ationale

-0.19

ATRIX

-0.17

wend

-0.16

onda

-0.15

Ð½Ð°ÑĩÐµ

-0.14

cÄ±

-0.14

İ

-0.14

TION

-0.14

wagon

-0.14

zbek

-0.14

POSITIVE LOGITS

 chief

0.37

 among

0.36

 ones

0.34

 Ð½Ð°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.33

one

0.33

 including

0.32

 Among

0.31

 such

0.31

 amongst

0.31

 foremost

0.31

Activations Density 0.276%

statements and propositions related to potential issues and explanations

No Comments

No Known Activations