INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÑĥÐ¼Ð¾Ð²

-0.15

omen

-0.15

mund

-0.15

iven

-0.15

edy

-0.15

igne

-0.14

uib

-0.14

king

-0.14

 Provided

-0.14

ora

-0.14

POSITIVE LOGITS

lopedia

0.16

erer

0.16

 pars

0.16

apper

0.15

zyst

0.15

herits

0.15

arter

0.14

Duy

0.14

cela

0.14

 Wick

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.