INDEX

Explanations

key features of prominent places, events, and establishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 themselves

-0.15

eko

-0.14

quist

-0.14

rlen

-0.14

undy

-0.14

@register

-0.14

ICES

-0.14

idden

-0.14

ersen

-0.14

 Stam

-0.13

POSITIVE LOGITS

ä¹ĭä¸Ģ

0.34

-ever

0.19

 aller

0.18

ìĿ´ìŀĲ

0.17

 ever

0.17

 EVER

0.16

urement

0.15

à¤¤à¤®

0.15

KeyValue

0.15

aal

0.15

Activations Density 0.063%

key features of prominent places, events, and establishments

No Comments

No Known Activations