INDEX

Explanations

statements that assert truth or indicate validity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÑĢÐµÐ¼ÐµÐ½Ð½Ð¾

-0.13

Ø§Ø³Ùĩ

-0.13

 ÙħØ§ÙĨ

-0.13

 Ð¾Ð±Ð¾

-0.12

ëĭĺ

-0.12

 ê°ĻìĿ´

-0.12

 bÄĻdÄħ

-0.12

âĻ¡

-0.12

ÑĢÐ¸Ðº

-0.12

-à¤¬

-0.12

POSITIVE LOGITS

 that

0.65

that

0.50

tha

0.49

 than

0.48

tat

0.43

hat

0.43

 ráº±ng

0.40

	that

0.39

 bahwa

0.38

 thay

0.36

Activations Density 0.480%

statements that assert truth or indicate validity

No Comments

No Known Activations