INDEX

Explanations

technical terms and symbols related to mathematics and email usage

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

urovision

-0.15

å³°

-0.14

.ops

-0.14

cky

-0.14

izik

-0.14

allen

-0.13

abela

-0.13

 æ©

-0.13

oreal

-0.13

hetic

-0.13

POSITIVE LOGITS

Ð°ÑĤÐµÐ¼

0.15

@$_

0.15

bre

0.14

 impression

0.14

redient

0.14

 Rosenberg

0.14

 Jacob

0.14

 Crowley

0.13

ouser

0.13

à¹Ģà¸ĺà¸Ń

0.13

Activations Density 0.960%

technical terms and symbols related to mathematics and email usage

No Comments

No Known Activations