INDEX

Explanations

phrases related to providing guidance or suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

/Instruction

-0.18

unami

-0.17

slash

-0.15

anship

-0.14

IFA

-0.14

ableObject

-0.14

è¨Ģ

-0.14

halten

-0.14

ilha

-0.13

itÃ¤

-0.13

POSITIVE LOGITS

 idea

0.72

 Idea

0.58

idea

0.56

 notion

0.39

 indication

0.38

 ideas

0.37

 sense

0.36

 IDEA

0.35

 clue

0.32

 insight

0.31

Activations Density 0.148%

phrases related to providing guidance or suggestions

No Comments

No Known Activations

phrases related to providing guidance or suggestions

No Comments

No Known Activations