INDEX

Explanations

references to various groups of people involved in travel, business, healthcare, and community engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

inou

-0.15

zas

-0.14

 tumble

-0.14

EXPR

-0.14

Ã©is

-0.14

enze

-0.14

VISIBLE

-0.13

Å¯st

-0.13

ocy

-0.13

pty

-0.13

POSITIVE LOGITS

 looking

0.46

looking

0.40

 wanting

0.34

 Looking

0.33

Looking

0.32

who

0.31

 interested

0.31

-looking

0.30

 seeking

0.28

 interes

0.28

Activations Density 0.338%

references to various groups of people involved in travel, business, healthcare, and community engagement

No Comments

No Known Activations