INDEX

Explanations

references to groups and teamwork in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 âĹĦ

-0.15

ãĥ³ãĥģ

-0.14

 wÅĤa

-0.13

ãģĦãģ«

-0.13

 serialVersionUID

-0.12

Ð¾ÐºÐµ

-0.12

ãģ«ãģ¦

-0.12

gorm

-0.12

[*

-0.12

POSITIVE LOGITS

 then

0.39

 even

0.33

 also

0.32

 especially

0.32

 particularly

0.29

 thus

0.29

 thereby

0.28

then

0.28

 therefore

0.28

also

0.27

Activations Density 0.180%

references to groups and teamwork in different contexts

No Comments

No Known Activations