INDEX

Explanations

specific references to formal certifications and professional organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

crest

-0.15

Ð»Ð°ÑĤÑĥ

-0.15

ð

-0.14

lland

-0.14

adge

-0.14

edere

-0.14

uat

-0.14

rez

-0.14

.appspot

-0.13

ldre

-0.13

POSITIVE LOGITS

unker

0.14

ills

0.14

Leaks

0.14

æ®

0.14

uggle

0.14

ì§Ī

0.14

pt

0.14

uns

0.13

asty

0.13

Activations Density 0.286%

specific references to formal certifications and professional organizations

No Comments

No Known Activations