INDEX

Explanations

phrases related to establishing or creating something, particularly in a leadership or organizational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

dera

-0.17

inz

-0.16

idders

-0.15

ogle

-0.15

áº§y

-0.15

StateChanged

-0.14

usu

-0.14

cri

-0.14

venes

-0.13

fare

-0.13

POSITIVE LOGITS

tle

0.27

 aside

0.25

elah

0.24

 forth

0.22

embre

0.20

 Aside

0.18

aside

0.18

acher

0.17

iap

0.17

 sail

0.17

Activations Density 0.053%

phrases related to establishing or creating something, particularly in a leadership or organizational context

No Comments

No Known Activations