INDEX

Explanations

terms related to dentistry and dental procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

erb

-0.17

oÅ¾

-0.16

BUM

-0.16

OVE

-0.15

 Morg

-0.15

keit

-0.15

UAGE

-0.15

Ð¾Ð»Ð¸

-0.15

opers

-0.15

eway

-0.14

POSITIVE LOGITS

istry

0.33

ures

0.28

ition

0.25

ISTRY

0.23

ure

0.22

ists

0.19

URES

0.19

itions

0.18

ritic

0.18

ITION

0.18

Activations Density 0.003%

terms related to dentistry and dental procedures

No Comments

No Known Activations