INDEX

Explanations

references to pricing and economic value related to services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

istra

-0.15

ãĤĤãģĨ

-0.15

plib

-0.14

 autres

-0.14

ault

-0.14

zon

-0.14

omnia

-0.13

ojenÃŃ

-0.13

 altro

-0.13

Î¬ÏģÏĩ

-0.13

POSITIVE LOGITS

 some

0.45

some

0.40

 Some

0.38

æľīäºĽ

0.35

Some

0.34

.some

0.31

"Some

0.30

 each

0.30

 SOME

0.30

æľīçļĦ

0.29

Activations Density 0.236%

references to pricing and economic value related to services or products

No Comments

No Known Activations