INDEX

Explanations

phrases related to character experiences and life situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

à¸ģà¸£à¸£à¸¡

-0.15

/+

-0.15

nga

-0.14

ietet

-0.14

esub

-0.14

é¾Ħ

-0.13

actics

-0.13

éĿĪ

-0.13

abit

-0.13

uart

-0.13

POSITIVE LOGITS

 happy

0.24

 seeming

0.23

 perfect

0.23

 seemingly

0.23

 paradise

0.22

 nice

0.21

 perfectly

0.21

perfect

0.21

å¹¸ç¦ı

0.20

happy

0.20

Activations Density 0.310%

phrases related to character experiences and life situations

No Comments

No Known Activations