INDEX

Explanations

references to boots or booting processes, indicating a focus on footwear, bootstrapping, or startup-related themes

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

ÑıÐ²

-0.17

à¥Ģà¤ķà¤°à¤£

-0.15

hed

-0.15

ubble

-0.15

pare

-0.15

reich

-0.14

oice

-0.14

 boiler

-0.14

udas

-0.14

pel

-0.13

POSITIVE LOGITS

leg

0.35

camp

0.33

str

0.31

laces

0.29

legs

0.28

 camp

0.27

 camps

0.26

STR

0.24

iful

0.24

LEG

0.24

Activations Density 0.012%

references to boots or booting processes, indicating a focus on footwear, bootstrapping, or startup-related themes

No Comments

No Known Activations