INDEX

Explanations

mathematical notations and symbols related to differential forms and geometry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

pon

-0.16

ingleton

-0.15

 Spread

-0.14

LD

-0.14

mg

-0.14

Spread

-0.14

 spread

-0.14

thon

-0.14

POSITIVE LOGITS

antz

0.17

resco

0.16

itzer

0.16

MOZ

0.15

ajo

0.15

igham

0.15

STRU

0.15

ova

0.15

 Frederick

0.14

rtle

0.14

Activations Density 0.034%

mathematical notations and symbols related to differential forms and geometry

No Comments

No Known Activations