INDEX

Explanations

numerical and bibliographic information, particularly related to the physical characteristics of books

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 passing

-0.19

omba

-0.17

 Alter

-0.17

van

-0.16

 meaning

-0.15

gri

-0.15

del

-0.15

MR

-0.14

 Republic

-0.14

 early

-0.14

POSITIVE LOGITS

andan

0.18

vox

0.17

Cong

0.17

 Cloth

0.16

excel

0.15

 semiclass

0.15

 Cong

0.14

nda

0.14

egin

0.14

ripp

0.14

Activations Density 0.014%

numerical and bibliographic information, particularly related to the physical characteristics of books

No Comments

No Known Activations