INDEX

Explanations

phrases related to scientific claims and their reevaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

bah

-0.15

zo

-0.15

Prompt

-0.14

ascimento

-0.14

getBytes

-0.14

æ¢Ŀ

-0.14

 prompt

-0.14

 pneum

-0.13

 Bethlehem

-0.13

kus

-0.13

POSITIVE LOGITS

 published

0.16

published

0.15

\core

0.14

 peer

0.14

imuth

0.14

avis

0.14

ftp

0.13

alim

0.13

-peer

0.13

 Peer

0.13

Activations Density 0.015%

phrases related to scientific claims and their reevaluation

No Comments

No Known Activations