INDEX

Explanations

references to ongoing projects and their developments

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

 starting

-0.37

 Starting

-0.35

starting

-0.34

Starting

-0.33

 starters

-0.23

 Starts

-0.22

starts

-0.20

 Start

-0.20

 Starter

-0.20

/start

-0.19

POSITIVE LOGITS

beg

0.37

Beg

0.33

 begging

0.27

 beings

0.26

 stared

0.22

 stated

0.21

 star

0.21

BE

0.20

 unofficial

0.19

 stars

0.19

Activations Density 0.092%

references to ongoing projects and their developments

No Comments

No Known Activations