INDEX

Explanations

references to surveys, awards, and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 worldwide

-0.17

 Countries

-0.17

Countries

-0.16

åħ¨çĲĥ

-0.16

ustralian

-0.16

 Australian

-0.15

 Australia

-0.15

 Austral

-0.15

 Territories

-0.15

 Toronto

-0.15

POSITIVE LOGITS

 locally

0.31

 local

0.29

 Local

0.25

local

0.24

 county

0.24

 LOCAL

0.23

 city

0.22

Local

0.21

 downtown

0.21

 County

0.21

Activations Density 0.032%

references to surveys, awards, and recognition

No Comments

No Known Activations