INDEX

Explanations

terms associated with luxury, comfort, and wellness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ings

-0.18

tery

-0.15

/edit

-0.14

æ¬²

-0.14

Ð°Ð½Ñģ

-0.14

eres

-0.14

atis

-0.14

Reusable

-0.14

icom

-0.14

czy

-0.14

POSITIVE LOGITS

fully

0.18

à¸¸à¹ī

0.17

lessly

0.15

ful

0.15

ibly

0.14

ously

0.14

full

0.14

FUL

0.14

fulness

0.14

uous

0.14

Activations Density 0.294%

terms associated with luxury, comfort, and wellness

No Comments

No Known Activations