INDEX

Explanations

references to printing and downloadable content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

sk

-0.16

 Cord

-0.15

bow

-0.15

agoon

-0.14

 Colomb

-0.14

aine

-0.14

Ple

-0.14

asso

-0.14

Fib

-0.14

 indexed

-0.14

POSITIVE LOGITS

 print

0.32

 Print

0.30

 printing

0.29

 printer

0.28

 Printing

0.27

-print

0.27

_PRINT

0.26

/print

0.26

.print

0.26

printer

0.26

Activations Density 0.080%

references to printing and downloadable content

No Comments

No Known Activations