INDEX

Explanations

metrics related to scoring in competitive games

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

à¸£à¸°

-0.15

ishi

-0.15

Hoe

-0.14

linky

-0.14

BOTTOM

-0.14

Ã¶st

-0.14

åĪĢ

-0.14

chia

-0.14

æĸŃ

-0.14

kins

-0.13

POSITIVE LOGITS

 targets

0.52

 target

0.50

 Targets

0.47

Targets

0.43

target

0.41

targets

0.41

Target

0.40

 Target

0.40

/target

0.39

-target

0.37

Activations Density 0.100%

metrics related to scoring in competitive games

No Comments

No Known Activations