INDEX

Explanations

terms related to metabolic processes and fat management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Juice

-0.18

bler

-0.18

 juice

-0.17

cheme

-0.15

ermen

-0.14

aju

-0.14

Ble

-0.14

opaque

-0.14

ohl

-0.14

 juices

-0.14

POSITIVE LOGITS

 burning

0.31

 burn

0.30

fat

0.29

 Burning

0.28

burn

0.28

 burned

0.27

 burns

0.27

Burn

0.26

fat

0.26

 adip

0.25

Activations Density 0.044%

terms related to metabolic processes and fat management

No Comments

No Known Activations