INDEX

Explanations

phrases indicating player performance and setbacks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ordion

-0.16

SSIP

-0.16

.jquery

-0.15

 lands

-0.15

 illegal

-0.15

abaj

-0.15

esini

-0.14

utut

-0.14

apiro

-0.14

antor

-0.14

POSITIVE LOGITS

 career

0.18

 performances

0.18

 performans

0.17

 performance

0.17

 Performance

0.16

 lately

0.16

Performance

0.16

oola

0.16

 leash

0.16

 Career

0.15

Activations Density 0.022%

phrases indicating player performance and setbacks

No Comments

No Known Activations