INDEX

Explanations

mathematical symbols and notation related to sequences and limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

erce

-0.16

GuidId

-0.15

ãĥ¼ãĥī

-0.15

ãĤĵãģ©

-0.14

ullan

-0.14

Ã½t

-0.14

/XMLSchema

-0.14

Ø´ÙĨ

-0.14

Äĩi

-0.14

Sor

-0.14

POSITIVE LOGITS

 Gupta

0.15

 Hans

0.15

 Region

0.14

 nÃło

0.14

WSC

0.14

 åĬ

0.14

é

0.14

.TRUE

0.14

foil

0.14

Activations Density 0.150%

mathematical symbols and notation related to sequences and limits

No Comments

No Known Activations