INDEX

Explanations

terms related to forensics and medical legal matters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 scouts

-0.15

 Surgery

-0.14

 Judgment

-0.14

ãĤĵãģ¨

-0.14

 scouting

-0.14

ckill

-0.14

.Logic

-0.13

_parm

-0.13

Å¡Å¥

-0.13

POSITIVE LOGITS

DNA

0.40

DNA

0.32

dna

0.28

 forensic

0.26

 Fore

0.26

 fore

0.25

dna

0.24

 crime

0.23

 evidence

0.23

 FORE

0.22

Activations Density 0.018%

terms related to forensics and medical legal matters

No Comments

No Known Activations