INDEX

Explanations

numerical values and metadata associated with events, announcements, and community-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ache

-0.15

ÅĦ

-0.15

 relative

-0.15

nement

-0.14

rint

-0.14

ijkstra

-0.14

adox

-0.14

ÑĩÐ¸ÑĤ

-0.13

ieurs

-0.13

IGHT

-0.13

POSITIVE LOGITS

ERRU

0.19

how

0.16

&o

0.15

~~~~~~~~~~~~~~~~

0.15

 Episode

0.15

 part

0.15

orz

0.14

à¤¹à¤°

0.13

an

0.13

akah

0.13

Activations Density 0.252%

numerical values and metadata associated with events, announcements, and community-related information

No Comments

No Known Activations