INDEX

Explanations

technical terms and measurements related to scientific experiments and data analysis

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

Ð·Ð°Ð±

-0.14

å·¡

-0.14

DataExchange

-0.13

 NONINFRINGEMENT

-0.13

INavigation

-0.13

 Ø±Ùģ

-0.13

physical

-0.13

_rewrite

-0.13

igner

-0.13

 Trafford

-0.12

POSITIVE LOGITS

 word

0.32

 Word

0.29

 embeddings

0.26

 sentence

0.25

 lexical

0.25

 words

0.24

bag

0.24

Bag

0.24

Word

0.23

lex

0.23

Activations Density 0.008%

technical terms and measurements related to scientific experiments and data analysis

No Comments

No Known Activations