INDEX

Explanations

references to player statistics and performance data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Zero

-0.23

Zero

-0.22

 zero

-0.22

zer

-0.22

zero

-0.21

 ZERO

-0.19

zer

-0.18

 zeros

-0.18

-zero

-0.17

zeros

-0.16

POSITIVE LOGITS

0.16

IENT

0.15

gage

0.15

apiro

0.15

avage

0.15

sted

0.14

.GetBytes

0.14

Ð»Ð°Ð¶

0.14

vÄĽd

0.13

ews

0.13

Activations Density 0.141%

references to player statistics and performance data

No Comments

No Known Activations