INDEX

Explanations

terminology related to marketing and advertising concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

istÃ©

-0.16

 ÙħÙĨÙĩØ§

-0.14

atÄ±r

-0.14

chez

-0.13

enums

-0.13

parison

-0.13

 Certain

-0.13

eton

-0.12

 heraus

-0.12

äºĭåĭĻ

-0.12

POSITIVE LOGITS

 basically

0.28

 essentially

0.24

 simply

0.24

 defined

0.23

 used

0.23

defined

0.23

 gÃ¬

0.23

used

0.22

 refers

0.22

any

0.21

Activations Density 0.274%

terminology related to marketing and advertising concepts

No Comments

No Known Activations