INDEX

Explanations

numerical data or statistics related to various studies and research findings

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

oref

-0.16

ulan

-0.16

umas

-0.15

antis

-0.14

oke

-0.14

artin

-0.14

adox

-0.14

 Impl

-0.14

enty

-0.14

ieee

-0.14

POSITIVE LOGITS

ÑĥÐ·

0.17

Ð¿Ð½Ñı

0.15

inal

0.14

iba

0.14

ToOne

0.14

fuse

0.13

AILS

0.13

moi

0.13

 zÃ¡

0.13

ienes

0.13

Activations Density 0.017%

numerical data or statistics related to various studies and research findings

No Comments

No Known Activations