INDEX

Explanations

references to film and cinema-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 films

-0.27

 Films

-0.27

 Film

-0.26

 film

-0.25

 filmes

-0.22

Film

-0.21

 filme

-0.21

ses

-0.21

çĶµå½±

-0.21

Movies

-0.20

POSITIVE LOGITS

ic

0.38

aker

0.36

akers

0.36

ography

0.36

strip

0.35

aking

0.31

 noir

0.29

-maker

0.28

stri

0.28

fare

0.28

Activations Density 0.040%

references to film and cinema-related topics

No Comments

No Known Activations