INDEX

Explanations

terms related to medical and legal qualifications or certifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ÑĤÑı

-0.15

ternet

-0.15

neas

-0.15

 Ø§ÙĦØ¹Ø±Ø¨ÙĬØ©

-0.15

 Desert

-0.14

acers

-0.14

uos

-0.14

ipop

-0.14

uhe

-0.14

ØµÙĦ

-0.14

POSITIVE LOGITS

 Combination

0.15

lain

0.15

gem

0.15

combination

0.15

 Chapter

0.14

 combination

0.14

Chapter

0.14

ab

0.14

 Cooperative

0.14

Activations Density 0.093%

terms related to medical and legal qualifications or certifications

No Comments

No Known Activations