INDEX

Explanations

numerical representations related to scientific study results and protocols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

urve

-0.16

uzzi

-0.15

 Idle

-0.15

licit

-0.15

-mf

-0.15

onen

-0.15

lef

-0.14

Ñĥ

-0.14

iales

-0.14

licted

-0.14

POSITIVE LOGITS

ÐµÐ¹Ð½

0.16

 maiden

0.16

 Maiden

0.15

 heroine

0.14

£

0.14

ovan

0.14

kop

0.14

ettle

0.14

ov

0.13

 Boat

0.13

Activations Density 0.013%

numerical representations related to scientific study results and protocols

No Comments

No Known Activations