INDEX

Explanations

mentions and references to new products or methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ANJI

-0.15

 ãĢľ

-0.15

 Blasio

-0.15

 discrepan

-0.14

Ã¢r

-0.14

ÎºÎ¹

-0.14

hydr

-0.13

afil

-0.13

UBLE

-0.13

pNet

-0.13

POSITIVE LOGITS

 each

0.16

TM

0.14

ogh

0.14

arra

0.14

 konkrÃ©t

0.14

 TextInputType

0.13

...

0.13

&#

0.13

Âģ

0.13

acky

0.12

Activations Density 0.013%

mentions and references to new products or methods

No Comments

No Known Activations