INDEX

Explanations

technical terms or metrics related to measurements and estimations

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

ÑĤÑĥ

-0.15

EventListener

-0.14

NPR

-0.14

ukes

-0.14

ester

-0.13

.enum

-0.13

ither

-0.13

ABC

-0.13

 Samuel

-0.13

BBC

-0.13

POSITIVE LOGITS

 virtual

0.23

 cloud

0.21

 Virtual

0.20

 Electronic

0.18

 digital

0.18

Virtual

0.18

 electronic

0.18

irtual

0.17

virtual

0.17

 hypers

0.17

Activations Density 0.003%

technical terms or metrics related to measurements and estimations

No Comments

No Known Activations