INDEX

Explanations

concepts and discussions related to Indian philosophy and government

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÐµÐ²Ð¸Ñĩ

-0.17

OLD

-0.16

anson

-0.15

/fa

-0.15

old

-0.15

witter

-0.14

 Gradient

-0.14

ì§Ī

-0.14

PU

-0.14

POSITIVE LOGITS

ĶåĽŀ

0.15

 ADVISED

0.15

ë¦¬ìĸ´

0.14

 Appointment

0.14

reur

0.14

 opport

0.13

 Carey

0.13

.updateDynamic

0.13

ãĥĥãĤ«ãĥ¼

0.13

esk

0.13

Activations Density 0.277%

concepts and discussions related to Indian philosophy and government

No Comments

No Known Activations