INDEX

Explanations

instructions related to installation and usage processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Receive

-0.14

 helfen

-0.13

ãģªãģĦ

-0.13

receive

-0.13

ceive

-0.13

\CMS

-0.13

 Ð´Ð¾Ð¿Ð¾Ð¼Ð°Ð³

-0.13

 hear

-0.13

ToBounds

-0.13

 hatta

-0.12

POSITIVE LOGITS

 simply

0.40

you

0.36

 Simply

0.32

 just

0.30

Simply

0.28

 goto

0.25

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.25

you

0.25

 Just

0.25

we

0.25

Activations Density 0.204%

instructions related to installation and usage processes

No Comments

No Known Activations