INDEX

Explanations

instances of communication or informing in various contexts

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

 yourself

-0.37

your

-0.36

 your

-0.34

 Yourself

-0.33

Your

-0.32

 yourselves

-0.30

 Your

-0.29

ä½łçļĦ

-0.26

YOUR

-0.26

 Ð²Ð°ÑĪ

-0.25

POSITIVE LOGITS

you

0.45

YOU

0.37

 thee

0.33

æĤ¨

0.32

you

0.32

 báº¡n

0.27

YOU

0.27

 vous

0.27

ä½ł

0.27

You

0.26

Activations Density 0.266%

instances of communication or informing in various contexts

No Comments

No Known Activations