INDEX

Explanations

mentions of research activities and funding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

iais

-0.16

un

-0.16

rene

-0.16

efa

-0.16

ÐµÐ·

-0.15

ange

-0.15

agal

-0.15

ene

-0.15

ica

-0.15

abal

-0.15

POSITIVE LOGITS

er

0.17

 council

0.17

ourcem

0.16

chio

0.15

zym

0.15

ersed

0.15

0.14

able

0.14

anitize

0.14

istrovstvÃŃ

0.14

Activations Density 0.019%

mentions of research activities and funding

No Comments

No Known Activations