INDEX

Explanations

questions and inquiries

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

æķ·

-0.15

chl

-0.15

áº«

-0.13

 Rosenstein

-0.13

Ð¼Ð°

-0.13

 Studio

-0.13

è¶³

-0.13

opsis

-0.13

 cess

-0.13

POSITIVE LOGITS

rezent

0.15

.accuracy

0.14

ãģ£ãģ±

0.14

LECTION

0.14

ALAR

0.14

 paras

0.14

INET

0.13

libft

0.13

ØµÙĩ

0.13

csr

0.13

Activations Density 0.013%

questions and inquiries

No Comments

No Known Activations