INDEX

Explanations

references to exhibitions and publications related to the arts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ventus

-0.17

eyse

-0.16

">ÃĹ</

-0.14

erule

-0.14

ocha

-0.14

.EventArgs

-0.14

verity

-0.14

ÑģÐ°Ð¼

-0.14

erialization

-0.13

áº«u

-0.13

POSITIVE LOGITS

 appeared

0.24

 numerous

0.24

 feature

0.24

 frequently

0.23

 appearances

0.22

 regularly

0.22

 appearing

0.22

 countless

0.22

 featured

0.21

 repeatedly

0.21

Activations Density 0.140%

references to exhibitions and publications related to the arts

No Comments

No Known Activations