INDEX

Explanations

references to reading and watching media

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

è¸ı

-0.16

bia

-0.16

UPI

-0.14

dale

-0.14

ë§ŀ

-0.14

agate

-0.14

 perish

-0.13

Argb

-0.13

 kiss

-0.13

illance

-0.13

POSITIVE LOGITS

 unfold

0.17

parts

0.16

 twice

0.16

ehr

0.16

é¡º

0.15

unfold

0.15

vor

0.15

 ÙĥØ§ÙħÙĦ

0.15

ogle

0.15

 ì²ľ

0.14

Activations Density 0.163%

references to reading and watching media

No Comments

No Known Activations