INDEX

Explanations

references to organizations, places, and events along with potential transactional elements

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

adal

-0.17

ulo

-0.16

 Casey

-0.15

-floating

-0.14

Bek

-0.14

 Knox

-0.14

iesen

-0.14

ritch

-0.14

enny

-0.14

ixe

-0.14

POSITIVE LOGITS

vale

0.18

ãĥ¼ãĥ

0.16

zhou

0.14

éĻ¶

0.14

itet

0.14

brains

0.14

XMLLoader

0.14

indexes

0.14

others

0.14

stva

0.14

Activations Density 0.369%

references to organizations, places, and events along with potential transactional elements

No Comments

No Known Activations