INDEX

Explanations

commands and instructions related to software configuration and management

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

olecules

-0.13

multipart

-0.13

á»§ng

-0.12

à¤¶à¤ķ

-0.12

Reviews

-0.12

 blackmail

-0.12

 UIResponder

-0.12

 Arthropoda

-0.12

 RuntimeMethod

-0.12

ContentLoaded

-0.11

POSITIVE LOGITS

 settings

0.54

 preferences

0.44

 setting

0.43

 Settings

0.41

settings

0.40

-settings

0.38

 preference

0.36

 Preferences

0.35

_settings

0.35

Settings

0.34

Activations Density 0.173%

commands and instructions related to software configuration and management

No Comments

No Known Activations