INDEX

Explanations

instances of the word "few" suggesting a focus on quantity or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ongo

-0.16

gio

-0.14

ati

-0.14

 Plenty

-0.14

/OR

-0.14

ong

-0.14

 Forgot

-0.14

ORIES

-0.13

cid

-0.13

POSITIVE LOGITS

 dozen

0.37

 hundred

0.27

 thousand

0.24

/all

0.19

 Hundred

0.18

 mÃ¡lo

0.18

 different

0.18

 extra

0.17

 Ð´ÐµÑģÑıÑĤ

0.17

est

0.17

Activations Density 0.059%

instances of the word "few" suggesting a focus on quantity or examples

No Comments

No Known Activations