INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 COVID

-0.66

 Covid

-0.65

 covid

-0.63

COVID

-0.57

-0.55

 pandemic

-0.53

 Coronavirus

-0.48

 coronavirus

-0.47

 Biden

-0.42

ovid

-0.41

POSITIVE LOGITS

0.44

Û²Û°Û±

0.34

 âĢª

0.28

 Huffington

0.26

 tumblr

0.24

 Tillerson

0.24

 Hollande

0.24

 Obama

0.24

 http

0.23

umblr

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.