INDEX

Explanations

instances of the word "on" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.24

ei

-0.23

tone

-0.23

eing

-0.19

een

-0.19

es

-0.19

ton

-0.18

uality

-0.18

eum

-0.18

ty

-0.17

POSITIVE LOGITS

ymous

0.27

imbus

0.26

uevo

0.24

nection

0.24

ucle

0.23

etwork

0.22

ese

0.21

ascimento

0.21

ics

0.21

avigation

0.21

Activations Density 0.142%

instances of the word "on" and its variations

No Comments

No Known Activations