INDEX

Explanations

terms related to eye health and vision

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

 laps

-0.15

dub

-0.14

rottle

-0.14

ìĺ¥

-0.13

 lapse

-0.13

lain

-0.13

ç«ł

-0.13

ëĮ

-0.13

lap

-0.13

POSITIVE LOGITS

ret

0.38

 retina

0.35

mac

0.30

Ret

0.29

_ret

0.28

ret

0.27

 chor

0.26

AMD

0.26

Ret

0.26

-ret

0.25

Activations Density 0.015%

terms related to eye health and vision

No Comments

No Known Activations