INDEX

Explanations

statistical references related to budget and approval ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ike

-0.16

...

-0.15

se

-0.15

 zero

-0.15

unb

-0.14

iral

-0.14

Ãĸ

-0.14

ALT

-0.14

POSITIVE LOGITS

ìĹŃ

0.16

ActiveSheet

0.16

akter

0.16

COMPARE

0.15

_VM

0.15

compare

0.15

 compares

0.15

ervo

0.15

èĤ©

0.15

Compare

0.14

Activations Density 0.059%

statistical references related to budget and approval ratings

No Comments

No Known Activations