INDEX

Explanations

terms related to academia and research across various disciplines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

atti

-0.15

 Svens

-0.15

qed

-0.15

 Shib

-0.15

Ã¥l

-0.15

 Ekon

-0.14

ific

-0.14

imity

-0.14

imen

-0.14

iset

-0.14

POSITIVE LOGITS

 Studies

0.23

 studies

0.21

Studies

0.17

omics

0.15

rell

0.15

annes

0.15

vana

0.15

inton

0.14

à¤ļà¤¨

0.14

 Fant

0.14

Activations Density 0.145%

terms related to academia and research across various disciplines

No Comments

No Known Activations