INDEX

Explanations

numerical data related to production and economics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

afe

-0.14

ardash

-0.14

 Glover

-0.14

 Spar

-0.14

_warnings

-0.14

pak

-0.14

 POLL

-0.14

 Miles

-0.13

avax

-0.13

commended

-0.13

POSITIVE LOGITS

/Index

0.18

 basis

0.17

kt

0.16

bps

0.16

basis

0.16

elsen

0.15

 Basis

0.15

ÐµÐºÐ¾Ð¼

0.15

zia

0.15

umo

0.15

Activations Density 0.145%

numerical data related to production and economics

No Comments

No Known Activations

numerical data related to production and economics

No Comments

No Known Activations