INDEX

Explanations

occurrences of the verb "make" and its variations, indicating emotional changes or responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iner

-0.17

iton

-0.16

¥¤

-0.16

acl

-0.16

../../../../

-0.15

udu

-0.15

uchar

-0.15

repid

-0.14

,None

-0.14

agram

-0.14

POSITIVE LOGITS

us

0.27

me

0.26

 sense

0.21

 otherwise

0.20

 people

0.19

 them

0.18

you

0.18

otherwise

0.17

him

0.17

 OTHERWISE

0.16

Activations Density 0.051%

occurrences of the verb "make" and its variations, indicating emotional changes or responses

No Comments

No Known Activations