INDEX

Explanations

references to sporting events, particularly the Commonwealth Games and athletes' achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

isco

-0.22

Ã³

-0.18

Ð¾ÑĢÐ´

-0.15

aps

-0.14

aterial

-0.14

âĹĭ

-0.14

lem

-0.14

jango

-0.14

icao

-0.14

Ð±ÐµÑĢ

-0.14

POSITIVE LOGITS

 Games

0.28

Games

0.26

 games

0.24

games

0.21

 Baton

0.20

 Commonwealth

0.18

	Common

0.17

_Common

0.17

Common

0.16

/Common

0.16

Activations Density 0.012%

references to sporting events, particularly the Commonwealth Games and athletes' achievements

No Comments

No Known Activations