INDEX

Explanations

noteworthiness and accomplishments of individuals within specific contexts such as entertainment, media, and community leadership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

rada

-0.16

Ð¼Ð¾Ñģ

-0.15

åĨĮ

-0.15

rape

-0.15

uxt

-0.15

Ø´Ùħ

-0.14

åĩ¡

-0.14

)const

-0.14

ASK

-0.14

Ð°Ð½ÑĤÐ°

-0.14

POSITIVE LOGITS

 talk

0.43

 talks

0.38

 discuss

0.36

 talked

0.35

 talking

0.35

talk

0.33

 discusses

0.32

 speak

0.32

 Talk

0.32

 spoke

0.31

Activations Density 0.224%

noteworthiness and accomplishments of individuals within specific contexts such as entertainment, media, and community leadership

No Comments

No Known Activations