INDEX

Explanations

names of prominent individuals and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

alink

-0.16

yw

-0.15

Da

-0.15

angl

-0.15

½æķ°

-0.14

Guy

-0.14

ieg

-0.14

 Downs

-0.14

rio

-0.14

ls

-0.14

POSITIVE LOGITS

kit

0.16

ĮĴ

0.15

llib

0.15

erland

0.14

(QL

0.14

andum

0.14

Ã¥l

0.14

ehler

0.14

 Tradable

0.14

Activations Density 0.007%

names of prominent individuals and their roles

No Comments

No Known Activations