INDEX

Explanations

expressions related to news or important information

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

adamente

-0.17

ucht

-0.14

acomment

-0.13

CallCheck

-0.13

odash

-0.13

ipel

-0.13

.Aggressive

-0.13

 Î£Ïĩ

-0.13

Ã¢m

-0.12

ÐĴÐŀ

-0.12

POSITIVE LOGITS

 news

0.77

news

0.55

-news

0.49

 NEWS

0.47

 News

0.44

(news

0.42

_news

0.41

.news

0.41

/news

0.39

 announcement

0.38

Activations Density 0.166%

expressions related to news or important information

No Comments

No Known Activations

expressions related to news or important information

No Comments

No Known Activations