INDEX

Explanations

numerical data and statistics related to individuals and films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.googlecode

-0.15

uracy

-0.14

yr

-0.14

uche

-0.14

lesh

-0.14

znik

-0.13

ime

-0.13

ÙģØ¹

-0.13

edm

-0.13

 fluid

-0.13

POSITIVE LOGITS

etto

0.15

Ð´ÑĸÐ»

0.14

Civ

0.14

utenberg

0.14

 íķĺëĤĺ

0.14

Î¶Î±

0.14

ACHER

0.14

unu

0.14

exampleInputEmail

0.14

 Surface

0.13

Activations Density 0.062%

numerical data and statistics related to individuals and films

No Comments

No Known Activations