INDEX

Explanations

references to independent or indie artistic works, including music, films, and games

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 likelihood

-0.17

au

-0.16

ly

-0.16

rai

-0.15

rouw

-0.15

rl

-0.14

unga

-0.14

arging

-0.14

nt

-0.14

POSITIVE LOGITS

vore

0.18

/small

0.17

Ã©gor

0.15

á½¶

0.15

ustos

0.14

tog

0.14

CJK

0.14

ofile

0.14

isode

0.14

ocker

0.14

Activations Density 0.011%

references to independent or indie artistic works, including music, films, and games

No Comments

No Known Activations