INDEX

Explanations

terms related to software licenses and copyright information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ocha

-0.15

fra

-0.15

qu

-0.15

à¸¤

-0.14

velt

-0.14

endif

-0.14

 Holmes

-0.14

apt

-0.13

 pitch

-0.13

POSITIVE LOGITS

ÛĮÙĩ

0.15

merc

0.15

UPER

0.15

upe

0.15

 vidÃ©os

0.14

inya

0.14

 Forecast

0.14

å¥´

0.14

uper

0.14

DAC

0.14

Activations Density 0.186%

terms related to software licenses and copyright information

No Comments

No Known Activations