INDEX

Explanations

references to catalogs and cataloging in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Å¡ak

-0.17

leck

-0.15

aney

-0.15

 skip

-0.15

 Skip

-0.15

 Robin

-0.14

blade

-0.14

 cons

-0.14

 blessed

-0.14

ayacak

-0.13

POSITIVE LOGITS

ews

0.15

Î¬ÏĤ

0.15

enser

0.15

 RequestMethod

0.14

enate

0.14

DataTask

0.14

cÃŃ

0.14

elib

0.14

cheid

0.14

ersen

0.14

Activations Density 0.004%

references to catalogs and cataloging in various contexts

No Comments

No Known Activations