INDEX

Explanations

terms related to epilepsy and seizure activities

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

orz

-0.15

bjerg

-0.15

tron

-0.15

kok

-0.14

ewis

-0.14

.dataTables

-0.14

acre

-0.14

orta

-0.14

Ho

-0.13

nost

-0.13

POSITIVE LOGITS

 epile

0.47

 epilepsy

0.46

 seizure

0.44

 seizures

0.44

Ep

0.33

 seizing

0.28

 seize

0.28

 seiz

0.27

 conv

0.27

 seized

0.26

Activations Density 0.028%

terms related to epilepsy and seizure activities

No Comments

No Known Activations