INDEX

Explanations

concepts related to optimization and mathematical functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

olo

-0.15

Ã¡t

-0.15

 mÄĽ

-0.14

Tie

-0.14

TypeDef

-0.14

 pomp

-0.14

 const

-0.13

undi

-0.13

aseline

-0.13

ãģĨãĤĵ

-0.13

POSITIVE LOGITS

estone

0.16

enko

0.16

emain

0.15

orado

0.15

adius

0.15

><?

0.14

oder

0.13

RTC

0.13

 Ø´ÛĮØ±

0.13

 ruce

0.13

Activations Density 0.006%

concepts related to optimization and mathematical functions

No Comments

No Known Activations