INDEX

Explanations

terms related to media production and broadcasting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

idal

-0.17

anske

-0.16

ìĿ´ìĬ¤

-0.16

PCA

-0.15

etooth

-0.15

èŃ·

-0.14

å¥ı

-0.14

kening

-0.14

 Merchant

-0.14

rog

-0.14

POSITIVE LOGITS

 production

0.25

OB

0.24

 studio

0.24

 Production

0.24

 studios

0.24

 productions

0.24

 Broadcast

0.23

 Studio

0.23

 Grass

0.23

 workflow

0.22

Activations Density 0.013%

terms related to media production and broadcasting

No Comments

No Known Activations