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

 char

-0.16

argin

-0.16

kus

-0.16

LayoutPanel

-0.15

 WithEvents

-0.14

Ð»Ð°Ð´Ð°

-0.14

olland

-0.14

Å¡il

-0.14

hoe

-0.14

 kidd

-0.14

POSITIVE LOGITS

bons

0.16

apur

0.15

-fashion

0.15

itra

0.15

.tm

0.15

ahy

0.14

_OW

0.14

ardu

0.14

ascade

0.14

_dll

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.