INDEX

Explanations

references to significant historical events and scandals

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

Ð¾Ð±Ñĭ

-0.15

_inline

-0.15

_Static

-0.14

 oppress

-0.14

 assail

-0.14

ÙĪØ§Ø±

-0.14

'gc

-0.14

 ATTACK

-0.14

 homicides

-0.14

xia

-0.14

POSITIVE LOGITS

 scandal

0.42

 scandals

0.40

 scand

0.32

 revelations

0.25

gate

0.24

 corruption

0.23

 allegations

0.23

 controversy

0.22

Gate

0.21

 controversies

0.21

Activations Density 0.284%

references to significant historical events and scandals

No Comments

No Known Activations