INDEX

Explanations

words related to treating or providing care to others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

itorio

-0.17

æ´¥

-0.16

opa

-0.16

hiro

-0.15

rians

-0.15

evice

-0.15

.ov

-0.14

ãģĦãĤĭ

-0.14

chia

-0.14

swagen

-0.14

POSITIVE LOGITS

ise

0.27

ises

0.26

 treat

0.24

 Treat

0.21

ISE

0.20

 treats

0.18

 treated

0.18

ments

0.18

maker

0.18

 treating

0.17

Activations Density 0.031%

words related to treating or providing care to others

No Comments

No Known Activations