INDEX

Explanations

variations of the word "regardless."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uma

-0.17

ijn

-0.17

tron

-0.17

uary

-0.16

Ð¾Ð²ÑĸÐ´

-0.16

tra

-0.16

ropol

-0.15

jin

-0.15

ographies

-0.14

pany

-0.14

POSITIVE LOGITS

 whether

0.26

whether

0.22

how

0.20

ä¹İ

0.19

LY

0.18

 Whether

0.18

Whether

0.18

ness

0.18

lessly

0.17

æĺ¯åĲ¦

0.17

Activations Density 0.006%

variations of the word "regardless."

No Comments

No Known Activations