INDEX

Explanations

No Explanations Found

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

 Corona

-0.18

Uk

-0.17

 Covid

-0.17

 Corbyn

-0.16

CPR

-0.16

Canadian

-0.15

cor

-0.15

 Linkedin

-0.15

 Coronavirus

-0.15

Cd

-0.14

POSITIVE LOGITS

PH

0.23

 Public

0.22

PH

0.20

variant

0.19

 public

0.19

 rede

0.19

Hin

0.19

variants

0.19

 variant

0.19

 variants

0.19

Activations Density 0.006%

No Comments

No Known Activations