INDEX

Explanations

elements related to community and collaboration in projects or activities

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

 itself

-0.37

çļĦä¸Ģä¸ª

-0.23

å®ĥ

-0.19

its

-0.19

æĺ¯ä¸ª

-0.18

æĺ¯ä¸Ģä¸ª

-0.18

 Everything

-0.17

ä¸Ģä¸ªäºº

-0.17

ä¸ĢåĢĭ

-0.16

 someone

-0.16

POSITIVE LOGITS

 themselves

0.52

 ones

0.32

 thems

0.26

ones

0.25

äºĽ

0.25

 examples

0.23

 respectively

0.22

åĪĨåĪ«

0.22

 nhá»¯ng

0.21

 yourselves

0.21

Activations Density 1.052%

elements related to community and collaboration in projects or activities

No Comments

No Known Activations