INDEX

Explanations

positive descriptors and references to performance metrics in sports-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

usa

-0.15

ulus

-0.14

ustos

-0.14

gtest

-0.14

eldon

-0.14

umas

-0.13

rams

-0.13

 Äĳá»Ŀi

-0.13

aÅŁ

-0.13

Ð°ÑĢÐ°Ð¼

-0.13

POSITIVE LOGITS

 performance

0.65

 performances

0.55

performance

0.54

 effort

0.50

 Performance

0.50

Performance

0.46

 showing

0.44

 PERFORMANCE

0.43

-performance

0.43

 performan

0.42

Activations Density 0.145%

positive descriptors and references to performance metrics in sports-related contexts

No Comments

No Known Activations