INDEX

Explanations

references to paper products or materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

sb

-0.20

eva

-0.20

sin

-0.18

sa

-0.18

sf

-0.18

sing

-0.17

spb

-0.17

sla

-0.17

sy

-0.17

tics

-0.17

POSITIVE LOGITS

clip

0.39

weight

0.35

backs

0.34

weights

0.31

trail

0.29

 towel

0.28

board

0.27

 towels

0.26

mill

0.26

work

0.26

Activations Density 0.026%

references to paper products or materials

No Comments

No Known Activations