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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ager

-0.16

-0.15

chor

-0.15

eking

-0.14

SSION

-0.14

REP

-0.14

ÎµÎº

-0.14

ÎºÎ»Î·

-0.14

ogo

-0.13

Haz

-0.13

POSITIVE LOGITS

 awards

0.31

 Awards

0.31

 nominations

0.20

 Golden

0.20

 ceremony

0.19

 Critics

0.19

 Readers

0.17

 Guild

0.17

 voting

0.17

 Webb

0.17

Activations Density 0.058%

references to awards and nominations in film and television

No Comments

No Known Activations