INDEX

Explanations

references to higher education programs and international collaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

è£ı

-0.16

bib

-0.15

ibox

-0.15

onom

-0.15

olla

-0.15

 pole

-0.15

auer

-0.15

ekil

-0.15

amat

-0.14

antar

-0.14

POSITIVE LOGITS

emand

0.15

 kÃ¼r

0.15

à¸Ķ

0.14

stub

0.14

ender

0.14

 kolo

0.14

_yield

0.14

ENCIL

0.14

utto

0.14

attern

0.13

Activations Density 0.215%

references to higher education programs and international collaborations

No Comments

No Known Activations