INDEX

Explanations

numerical references and citations within academic or formal texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 sixth

-0.37

-0.36

 Sixth

-0.34

SIX

-0.34

six

-0.33

 åħŃ

-0.32

åħŃ

-0.32

-six

-0.30

Six

-0.30

 seventh

-0.29

POSITIVE LOGITS

0.26

ç¬¬äºĮ

0.24

 second

0.23

II

0.22

 Second

0.22

âĳ¡

0.21

äºĮ

0.20

 ç¬¬äºĮ

0.20

Û²

0.19

Activations Density 0.096%

numerical references and citations within academic or formal texts

No Comments

No Known Activations