INDEX

Explanations

references to awards and nominations in film and television

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rint

-0.16

CLUDED

-0.15

azor

-0.14

ToFront

-0.14

 Tradable

-0.14

Attrs

-0.13

oge

-0.13

 absorbed

-0.13

 Lair

-0.13

udem

-0.13

POSITIVE LOGITS

 Academy

0.39

 Oscar

0.36

 Grammy

0.35

 Gram

0.35

Gram

0.34

 Emmy

0.34

 gram

0.32

 Oscars

0.31

 academy

0.31

 Prim

0.30

Activations Density 0.098%

references to awards and nominations in film and television

No Comments

No Known Activations