INDEX

Explanations

references to technical processes and system functionalities

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

ak

-0.16

PLE

-0.15

.ak

-0.15

 AuthenticationService

-0.15

artner

-0.14

 dÃ¶n

-0.14

egg

-0.14

æĬ¤

-0.14

zzle

-0.14

itin

-0.13

POSITIVE LOGITS

 test

0.20

:test

0.16

 TEST

0.16

 thá»Ń

0.16

)test

0.15

testdata

0.15

 tester

0.15

 testing

0.15

test

0.15

æµĭè¯ķ

0.15

Activations Density 0.151%

references to technical processes and system functionalities

No Comments

No Known Activations