INDEX

Explanations

phrases and terms related to communication, documentation, and announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

GetInt

-0.15

Ð¾Ð¼ÐµÐ½

-0.14

reso

-0.14

rab

-0.14

.sharedInstance

-0.14

æİ

-0.14

ewis

-0.13

hind

-0.13

uxe

-0.13

 Parker

-0.13

POSITIVE LOGITS

trl

0.16

ĥ

0.16

eras

0.16

ãĥ¬ãĥĥãĥĪ

0.15

INGER

0.15

ÎºÎ¿Î»

0.15

antino

0.15

á»¹

0.14

 Coleman

0.14

ascus

0.14

Activations Density 0.206%

phrases and terms related to communication, documentation, and announcements

No Comments

No Known Activations