INDEX

Explanations

terms related to community involvement and technological engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

æ¶ī

-0.16

azo

-0.16

amar

-0.14

à¸²à¸«

-0.14

urette

-0.14

lander

-0.14

.tt

-0.14

xes

-0.14

ULER

-0.14

enne

-0.13

POSITIVE LOGITS

 ranks

0.37

 fray

0.23

 forces

0.23

 fold

0.19

chor

0.18

 chorus

0.18

anks

0.17

forces

0.17

 queue

0.17

 mailing

0.17

Activations Density 0.049%

terms related to community involvement and technological engagement

No Comments

No Known Activations