INDEX

Explanations

references to notable individuals and organizations involved in conflict or terrorism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.15

Ø±ÙģØªÙĩ

-0.15

iversal

-0.14

 Bols

-0.14

ISIS

-0.13

 muslim

-0.13

_converter

-0.13

avad

-0.13

urma

-0.13

POSITIVE LOGITS

bin

0.29

Bin

0.27

al

0.25

Bin

0.23

 Abbott

0.23

bin

0.23

 Laden

0.21

-bin

0.21

AQ

0.20

UBL

0.20

Activations Density 0.013%

references to notable individuals and organizations involved in conflict or terrorism

No Comments

No Known Activations