INDEX

Explanations

complex and technical terms related to health and medical subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð¾Ð¶

-0.16

 Investors

-0.15

 Investor

-0.15

Unavailable

-0.13

 defaultMessage

-0.13

æ¡£

-0.13

 Ð´Ð¾Ð³

-0.13

emes

-0.13

ê¸ī

-0.13

 Listing

-0.13

POSITIVE LOGITS

 usage

0.27

 totals

0.26

 Usage

0.22

 activity

0.22

 numbers

0.22

 volumes

0.21

_usage

0.21

usage

0.21

 misuse

0.21

Usage

0.20

Activations Density 0.015%

complex and technical terms related to health and medical subjects

No Comments

No Known Activations