INDEX

Explanations

specific measurements and quantities related to ingredients or products

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

ROTO

-0.16

kms

-0.14

altung

-0.14

agos

-0.14

ë¹ł

-0.14

edii

-0.14

imeters

-0.14

oola

-0.13

_CRITICAL

-0.13

 kissing

-0.13

POSITIVE LOGITS

oz

0.38

 gram

0.38

 Gram

0.37

oz

0.35

 fluid

0.33

gram

0.33

Gram

0.32

 gramm

0.31

Oz

0.31

 grams

0.30

Activations Density 0.064%

specific measurements and quantities related to ingredients or products

No Comments

No Known Activations