INDEX

Explanations

phrases indicating direction or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

entai

-0.19

adir

-0.16

è¦º

-0.14

Ø§ÙħÛĮ

-0.14

engkap

-0.14

WithEmail

-0.14

amak

-0.13

chg

-0.13

,LOCATION

-0.13

é§

-0.13

POSITIVE LOGITS

see

0.22

ting

0.19

see

0.19

 retrieve

0.18

 deliver

0.17

 witness

0.16

See

0.16

 experience

0.16

 photograph

0.16

 confront

0.16

Activations Density 0.191%

phrases indicating direction or purpose

No Comments

No Known Activations