INDEX

Explanations

navigational elements and references to the homepage in the text

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

acific

-0.14

burg

-0.14

æĸ¹

-0.13

 Ãĸr

-0.13

lic

-0.13

essim

-0.13

 dziew

-0.13

izons

-0.13

 $("<

-0.13

tr

-0.13

POSITIVE LOGITS

0.23

 Â»

0.21

 Page

0.21

 âĪ

0.21

 arrow

0.21

 âĢº

0.21

 âĨĴ

0.21

 page

0.19

page

0.19

Activations Density 0.009%

navigational elements and references to the homepage in the text

No Comments

No Known Activations