INDEX

Explanations

instances of the word "Does" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

éĤ£äºĽ

-0.20

those

-0.17

these

-0.17

vala

-0.16

ÏĦÎ®ÏĥÎµÎ¹ÏĤ

-0.16

You

-0.15

ä»¬

-0.15

them

-0.14

here

-0.14

 amounts

-0.14

POSITIVE LOGITS

nt

0.31

 anyone

0.29

 anybody

0.28

/do

0.25

 Anyone

0.20

 everyone

0.19

Anyone

0.19

 everybody

0.18

/w

0.18

/is

0.18

Activations Density 0.023%

instances of the word "Does" in various contexts

No Comments

No Known Activations