INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iggs

-0.15

avic

-0.15

aqu

-0.14

ahn

-0.14

éģ£

-0.14

 aforementioned

-0.14

nun

-0.14

 james

-0.13

elfare

-0.13

_abort

-0.13

POSITIVE LOGITS

olean

0.15

0.14

æģ©

0.14

æľ¯

0.14

GN

0.14

 flows

0.13

 ÑĥÑģÐ»

0.13

Mesh

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.