INDEX

Explanations

terms related to governmental and environmental topics, particularly those concerning health, planning, and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

elda

-0.15

/problems

-0.14

 kiá»ĩn

-0.14

Ø¬ÙĦ

-0.14

ANNEL

-0.14

å®Ļ

-0.14

 Agricult

-0.13

oure

-0.13

åķı

-0.13

.PLL

-0.13

POSITIVE LOGITS

 department

0.26

 division

0.23

 ministry

0.21

 Department

0.21

 Division

0.21

å±Ģ

0.20

 dept

0.19

 office

0.19

 Dept

0.19

 agency

0.19

Activations Density 0.132%

terms related to governmental and environmental topics, particularly those concerning health, planning, and regulations

No Comments

No Known Activations