INDEX

Explanations

metrics and statistics related to student enrollment and educational success

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

cak

-0.17

ury

-0.15

 Willis

-0.15

ablish

-0.15

borg

-0.14

grade

-0.14

 Armour

-0.14

 associative

-0.14

Rig

-0.14

ÙĨØ§Ùħ

-0.14

POSITIVE LOGITS

tul

0.17

inkel

0.16

antal

0.16

ingles

0.15

holm

0.15

UpInside

0.15

Ð°Ð·Ð°

0.15

ìĿ´ë²Ħ

0.15

illos

0.15

 since

0.15

Activations Density 0.058%

metrics and statistics related to student enrollment and educational success

No Comments

No Known Activations