INDEX

Explanations

references to educational programs and academic indicators

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

taire

-0.15

Ð»ÑĥÐ³

-0.14

ospace

-0.13

heck

-0.13

OCK

-0.13

hend

-0.13

stry

-0.13

ansson

-0.13

aub

-0.13

inta

-0.12

POSITIVE LOGITS

 formerly

0.62

formerly

0.59

 former

0.58

 Former

0.58

Former

0.54

former

0.46

 erst

0.39

(form

0.35

 Ø³Ø§Ø¨ÙĤ

0.32

 bÃ½val

0.31

Activations Density 0.206%

references to educational programs and academic indicators

No Comments

No Known Activations