INDEX

Explanations

references to historical figures and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ahat

-0.15

@student

-0.14

ÅĽÄĩ

-0.14

inski

-0.14

å¢

-0.14

ollen

-0.13

endor

-0.13

Ð»Ñİ

-0.13

ÙĬØ±Ø§ÙĨ

-0.13

AINED

-0.13

POSITIVE LOGITS

 appointment

0.28

 appointments

0.24

 resign

0.23

 succeed

0.23

åħ¼

0.22

 until

0.21

 success

0.21

 vacancy

0.21

appointment

0.21

 succeeds

0.21

Activations Density 0.108%

references to historical figures and their roles

No Comments

No Known Activations