INDEX

Explanations

references to teams and teamwork

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

heed

-0.17

jÄĻ

-0.16

mey

-0.15

gressor

-0.15

xes

-0.15

aleza

-0.15

baum

-0.15

ances

-0.14

immer

-0.14

alles

-0.14

POSITIVE LOGITS

ä¼į

0.25

sters

0.23

ster

0.18

ka

0.17

à¸Ĭà¸²à¸ķ

0.17

perature

0.16

à¸ĩà¸²à¸Ļ

0.16

ings

0.15

pest

0.15

 member

0.15

Activations Density 0.068%

references to teams and teamwork

No Comments

No Known Activations