INDEX

Explanations

references to premium quality and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ucci

-0.15

iniz

-0.15

 Stanley

-0.14

ext

-0.14

->_

-0.13

.showMessage

-0.13

ernet

-0.13

ado

-0.13

gor

-0.13

İ

-0.13

POSITIVE LOGITS

vrier

0.17

hazi

0.17

ilib

0.15

cil

0.15

VRT

0.14

ighted

0.14

HG

0.14

Ã²a

0.14

ÃŃg

0.14

Ã¡g

0.14

Activations Density 0.005%

references to premium quality and related terms

No Comments

No Known Activations