INDEX

Explanations

references to historical events and figures associated with World War II and the Holocaust

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ilon

-0.17

onium

-0.16

Î¹Î±ÏĤ

-0.15

leniyor

-0.15

ofday

-0.14

edio

-0.14

GuidId

-0.14

regnum

-0.14

pter

-0.14

tica

-0.14

POSITIVE LOGITS

 previous

0.22

 Previous

0.21

 former

0.21

 earlier

0.21

Previous

0.20

previous

0.19

 erst

0.19

æĽ¾

0.18

 Ø³Ø§Ø¨ÙĤ

0.17

 original

0.16

Activations Density 0.386%

references to historical events and figures associated with World War II and the Holocaust

No Comments

No Known Activations