INDEX

Explanations

references to royal or ruling families and dynasties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iÅ¾

-0.17

-0.16

unden

-0.16

ered

-0.16

LES

-0.15

ELS

-0.15

PGA

-0.15

âĸį

-0.15

ÏĢÎµ

-0.15

erm

-0.15

POSITIVE LOGITS

ouser

0.17

atisation

0.14

setattr

0.14

Ã¨ne

0.14

IALOG

0.14

ãĥ©ãĤ¯

0.13

 COPYRIGHT

0.13

ousse

0.13

ÐºÐ¸Ð½

0.13

kim

0.13

Activations Density 0.003%

references to royal or ruling families and dynasties

No Comments

No Known Activations