INDEX

Explanations

terms related to racing and race cars

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

racial

-0.19

laÄį

-0.18

semb

-0.17

 racial

-0.17

 Races

-0.16

ten

-0.16

ness

-0.16

 Ø¹Ø§ÙħØ§

-0.15

ilter

-0.15

rlen

-0.15

POSITIVE LOGITS

course

0.45

way

0.37

courses

0.34

horse

0.34

car

0.34

cars

0.31

ways

0.31

card

0.26

craft

0.26

week

0.24

Activations Density 0.023%

terms related to racing and race cars

No Comments

No Known Activations