INDEX

Explanations

references to sports outcomes and playoff scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

arah

-0.17

 fastball

-0.17

 gazet

-0.15

swick

-0.15

.EventArgs

-0.15

 shel

-0.14

gro

-0.14

 karak

-0.14

yat

-0.14

annes

-0.14

POSITIVE LOGITS

 scenarios

0.24

 scenario

0.23

 Clin

0.23

 Scenario

0.23

 clin

0.23

tie

0.23

clin

0.22

Scenario

0.21

 mathematical

0.20

Tie

0.20

Activations Density 0.100%

references to sports outcomes and playoff scenarios

No Comments

No Known Activations