INDEX

Explanations

discussions about representation and diversity in media, particularly focusing on racial and gender issues within 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

armac

-0.17

ERRU

-0.15

áº¡n

-0.14

yyn

-0.14

ÐºÑĢÐµÑĤ

-0.14

__.__

-0.14

bellion

-0.13

pne

-0.13

frauen

-0.13

ileen

-0.13

POSITIVE LOGITS

 movies

0.42

 entertainment

0.36

 film

0.35

 movie

0.35

 films

0.35

movies

0.33

 Movies

0.31

æĺłçĶ»

0.30

 television

0.30

film

0.29

Activations Density 0.282%

discussions about representation and diversity in media, particularly focusing on racial and gender issues within film and television

No Comments

No Known Activations