INDEX

Explanations

terms related to epilepsy and seizures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ty

-0.16

ogany

-0.15

oger

-0.15

 wound

-0.14

erals

-0.14

rex

-0.14

hazi

-0.14

irl

-0.14

Ã¡p

-0.14

oggle

-0.14

POSITIVE LOGITS

 epilepsy

0.38

 epile

0.35

 seizure

0.34

 seizures

0.32

 ketogenic

0.23

Ep

0.20

 seizing

0.19

 seiz

0.18

 conv

0.18

gd

0.17

Activations Density 0.025%

terms related to epilepsy and seizures

No Comments

No Known Activations