INDEX

Explanations

references to geographic locations and political entities in a historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Claud

-0.15

åį

-0.14

antal

-0.14

 bones

-0.14

caff

-0.14

lat

-0.14

ForKey

-0.14

Yog

-0.13

 bare

-0.13

 Bones

-0.13

POSITIVE LOGITS

Invocation

0.16

ilit

0.14

ardo

0.14

 cole

0.14

andro

0.14

 Camp

0.14

.datatables

0.14

>window

0.14

åĿ

0.14

 Alternate

0.13

Activations Density 0.049%

references to geographic locations and political entities in a historical context

No Comments

No Known Activations