INDEX

Explanations

terms related to various medical diseases and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

åħ

-0.16

ahun

-0.15

inidad

-0.15

affles

-0.15

ALI

-0.14

rame

-0.14

 Watt

-0.14

abay

-0.14

 Abilities

-0.14

hab

-0.14

POSITIVE LOGITS

VB

0.19

 Dillon

0.15

à¸¡à¸Ń

0.15

-Compatible

0.14

eki

0.13

kÃ¶

0.13

 Jennings

0.13

 WaitForSeconds

0.13

Sid

0.13

pac

0.13

Activations Density 0.007%

terms related to various medical diseases and conditions

No Comments

No Known Activations