INDEX

Explanations

references to welding and manufacturing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-scrollbar

-0.16

noch

-0.16

estone

-0.15

vel

-0.15

ot

-0.15

åĭ

-0.15

 infr

-0.15

rega

-0.14

/gtest

-0.14

egg

-0.14

POSITIVE LOGITS

 welding

0.28

 Weld

0.27

 weld

0.26

 Plasma

0.20

Arc

0.20

 plasma

0.20

Arc

0.20

 torch

0.18

 welded

0.18

 pudd

0.18

Activations Density 0.018%

references to welding and manufacturing processes

No Comments

No Known Activations