INDEX

Explanations

names of professionals and entities in legal and medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

igli

-0.17

iol

-0.16

ilet

-0.15

rea

-0.15

outil

-0.14

ucht

-0.14

oub

-0.14

ØªØ¨Ùĩ

-0.14

DAQ

-0.14

/Resources

-0.14

POSITIVE LOGITS

affen

0.16

enum

0.16

Jr

0.16

.ll

0.15

orp

0.15

oled

0.15

orde

0.15

_asm

0.14

lasÄ±

0.14

Ltd

0.14

Activations Density 0.258%

names of professionals and entities in legal and medical contexts

No Comments

No Known Activations