INDEX

Explanations

instances of the word "put" in various forms, indicating actions of placing or establishing something

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

ories

-0.16

rsa

-0.16

itez

-0.15

ÑĢÐ´

-0.15

çĨŁ

-0.15

ials

-0.15

enders

-0.15

fter

-0.14

imeo

-0.14

aries

-0.14

POSITIVE LOGITS

 forth

0.32

 aside

0.32

 together

0.31

atively

0.30

tered

0.27

tering

0.26

ter

0.24

ty

0.23

ative

0.22

Together

0.22

Activations Density 0.042%

instances of the word "put" in various forms, indicating actions of placing or establishing something

No Comments

No Known Activations