INDEX

Explanations

references to various associations and organizations

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

ittel

-0.20

pon

-0.16

cape

-0.16

ISIBLE

-0.15

ãģĤãģ®

-0.14

ìĪł

-0.14

ekil

-0.14

rah

-0.13

.coroutines

-0.13

ITTER

-0.13

POSITIVE LOGITS

/group

0.16

ally

0.16

lig

0.16

-Pacific

0.16

ively

0.15

ê¸Ī

0.15

esthetic

0.15

.VisualBasic

0.14

ual

0.14

wahl

0.14

Activations Density 0.038%

references to various associations and organizations

No Comments

No Known Activations