INDEX

Explanations

medical terminology related to health conditions and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

íıĲ

-0.16

ÙĪÙħØ§Øª

-0.16

ussen

-0.16

ÃĹ↵↵

-0.15

nero

-0.14

ÐµÑĢÐ¾

-0.13

Ø¨ÙĪØ§Ø³Ø·Ø©

-0.13

UpInside

-0.13

Ott

-0.13

elan

-0.13

POSITIVE LOGITS

ol

0.81

OL

0.66

ole

0.65

ols

0.63

ol

0.62

Ð¾Ð»

0.62

oli

0.60

à¥ĭà¤²

0.57

ola

0.57

oll

0.56

Activations Density 0.172%

medical terminology related to health conditions and treatments

No Comments

No Known Activations