INDEX

Explanations

references to inclusivity and the concept of 'all'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ogne

-0.20

.native

-0.17

outu

-0.16

wner

-0.15

obus

-0.15

alogy

-0.15

à¥ģà¤°à¤¸

-0.15

orry

-0.15

ãĥ©ãĤ¹

-0.15

erais

-0.14

POSITIVE LOGITS

who

0.29

 involved

0.28

who

0.27

 ages

0.23

 whom

0.22

iets

0.21

 races

0.21

 sectors

0.21

 segments

0.21

types

0.21

Activations Density 0.076%

references to inclusivity and the concept of 'all'

No Comments

No Known Activations