INDEX

Explanations

instances of penalties and fouls in sports contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

InputDialog

-0.16

luk

-0.15

iane

-0.15

upal

-0.15

ISTA

-0.14

_traits

-0.14

ewire

-0.14

iture

-0.14

ola

-0.14

æĸŃ

-0.13

POSITIVE LOGITS

fou

0.26

Fou

0.26

 infra

0.25

 rough

0.24

 personal

0.23

 flag

0.22

 targeting

0.22

 foul

0.20

 flags

0.20

uns

0.20

Activations Density 0.034%

instances of penalties and fouls in sports contexts

No Comments

No Known Activations