INDEX

Explanations

terms related to Nazi Germany and historical events associated with it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

imos

-0.16

 Pascal

-0.15

okin

-0.15

ft

-0.15

ibble

-0.13

onaut

-0.13

 anarch

-0.13

orra

-0.13

 Merc

-0.13

/us

-0.13

POSITIVE LOGITS

 Hitler

0.47

Hit

0.41

 Nazi

0.41

 Nazis

0.38

naz

0.36

SS

0.35

Naz

0.35

Naz

0.35

NS

0.34

Hit

0.34

Activations Density 0.152%

terms related to Nazi Germany and historical events associated with it

No Comments

No Known Activations