INDEX

Explanations

content related to practical advice and tips

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

anca

-0.15

?>&

-0.14

::$

-0.14

/Search

-0.13

ä½ĵ

-0.13

æ´¥

-0.13

arda

-0.13

-added

-0.13

 tÃ½m

-0.13

 Added

-0.13

POSITIVE LOGITS

 every

0.18

tips

0.18

 anybody

0.18

how

0.17

to

0.17

 anyone

0.17

 tips

0.17

 everybody

0.17

 help

0.16

 shared

0.16

Activations Density 0.125%

content related to practical advice and tips

No Comments

No Known Activations