INDEX

Explanations

terms related to the film and entertainment industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 tiáº¿t

-0.15

oldem

-0.14

 Invent

-0.14

 Bicycle

-0.14

imin

-0.13

.Views

-0.13

 vacc

-0.13

Ã¡b

-0.13

itzer

-0.13

POSITIVE LOGITS

 radio

0.36

 motion

0.34

TV

0.27

radio

0.27

motion

0.26

 television

0.25

 Motion

0.24

 stage

0.24

 animation

0.23

 Radio

0.23

Activations Density 0.223%

terms related to the film and entertainment industry

No Comments

No Known Activations