INDEX

Explanations

references to events and their updates

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cÃ©

-0.16

/Dk

-0.15

Î¼ÏĮ

-0.14

_subscribe

-0.14

akis

-0.14

pany

-0.14

eniable

-0.14

Ã©li

-0.14

 Printable

-0.13

 mutated

-0.13

POSITIVE LOGITS

 posted

0.47

 posting

0.46

 upload

0.41

 post

0.39

-post

0.38

 poste

0.38

 uploaded

0.38

posted

0.37

 uploading

0.35

 posts

0.33

Activations Density 0.321%

references to events and their updates

No Comments

No Known Activations