INDEX

Explanations

instances of the word "Of" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oods

-0.16

oss

-0.16

pery

-0.16

icking

-0.15

illis

-0.15

OperationException

-0.15

lessly

-0.15

apon

-0.15

yer

-0.15

Ð¼Ð¸

-0.14

POSITIVE LOGITS

 course

0.29

 note

0.21

course

0.21

OURSE

0.20

icers

0.19

_Of

0.18

sted

0.17

 Course

0.17

.course

0.17

note

0.16

Activations Density 0.013%

instances of the word "Of" and variations of it

No Comments

No Known Activations