INDEX

Explanations

terms related to medical diagnoses and bodily injuries

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

zano

-0.17

Î³ÎºÎ±

-0.16

oste

-0.15

.AddListener

-0.14

dy

-0.14

oulos

-0.14

awner

-0.14

baugh

-0.13

ç£

-0.13

ugas

-0.13

POSITIVE LOGITS

 Zucker

0.16

 UsersController

0.14

orne

0.14

 quotient

0.14

egasus

0.14

 fare

0.13

erv

0.13

 HomeController

0.13

OAD

0.13

 Tanner

0.13

Activations Density 0.070%

terms related to medical diagnoses and bodily injuries

No Comments

No Known Activations