INDEX

Explanations

phrases indicating methods or approaches to achieving outcomes

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

INVAL

-0.15

ÑģÐµÐ½

-0.15

ëŀĢ

-0.14

xin

-0.14

urs

-0.14

AssignableFrom

-0.13

vrier

-0.13

rought

-0.13

Ø´ØªÙĩ

-0.13

à¸³

-0.13

POSITIVE LOGITS

 things

0.28

ward

0.27

 they

0.21

 mÃł

0.21

way

0.20

 that

0.20

 thing

0.20

we

0.19

(s

0.19

 people

0.18

Activations Density 0.035%

phrases indicating methods or approaches to achieving outcomes

No Comments

No Known Activations