INDEX

Explanations

elements related to rules and conditions in applications and submissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 sensit

-0.15

 Crescent

-0.15

 transit

-0.15

Ya

-0.15

wg

-0.14

 Conflict

-0.14

ya

-0.14

 opener

-0.14

POSITIVE LOGITS

chein

0.19

@nate

0.18

ardo

0.16

ceb

0.15

ACKET

0.15

acos

0.15

VarChar

0.14

OperationException

0.14

ynos

0.14

acco

0.14

Activations Density 0.188%

elements related to rules and conditions in applications and submissions

No Comments

No Known Activations