INDEX

Explanations

geographical and location-based references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Hills

-0.18

ä¸ĺ

-0.17

æ½®

-0.17

 sandy

-0.16

 Waves

-0.16

 tide

-0.16

 Beach

-0.15

 sand

-0.15

 leve

-0.15

 Tide

-0.15

POSITIVE LOGITS

 Alpine

0.27

al

0.24

ski

0.22

 cable

0.22

 mountain

0.22

 glacier

0.22

 valley

0.20

 Ð°Ð»ÑĮ

0.20

Rif

0.20

 summit

0.19

Activations Density 0.124%

geographical and location-based references

No Comments

No Known Activations