INDEX

Explanations

quantitative statistics related to sports performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ium

-0.22

eller

-0.15

roy

-0.15

roys

-0.14

rsp

-0.14

 Tang

-0.14

 Nose

-0.14

oten

-0.14

 mush

-0.14

yna

-0.14

POSITIVE LOGITS

 shooting

0.32

 shoot

0.30

 shoots

0.28

 Shooting

0.28

 Shoot

0.25

 shootings

0.24

hit

0.24

Shoot

0.24

 shot

0.23

 shooters

0.23

Activations Density 0.049%

quantitative statistics related to sports performance

No Comments

No Known Activations