INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Shaun

-0.16

Wie

-0.16

cido

-0.15

 Staples

-0.14

era

-0.14

Î½Î®

-0.14

lene

-0.14

du

-0.14

Jeremy

-0.14

len

-0.13

POSITIVE LOGITS

ziej

0.17

ako

0.16

olley

0.16

ENO

0.15

ÛĮÙĩ

0.15

brick

0.14

nano

0.14

 Seznam

0.14

esis

0.14

 dated

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.