INDEX

Explanations

questions and inquiries throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

zept

-0.18

Ð¾Ð´Ð°ÑĢ

-0.16

swire

-0.15

AndWait

-0.15

adele

-0.15

 ayrÄ±ca

-0.15

unday

-0.15

Ð¿ÑĢÐ°

-0.14

_DAC

-0.14

zie

-0.14

POSITIVE LOGITS

çļĦè¯Ŀ

0.26

 then

0.24

 perhaps

0.23

 Perhaps

0.22

 Then

0.22

 chances

0.21

 maybe

0.21

Then

0.21

Perhaps

0.20

 entonces

0.20

Activations Density 0.031%

questions and inquiries throughout the document

No Comments

No Known Activations