INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ìĨ

-0.17

ugo

-0.17

editable

-0.14

quee

-0.14

dent

-0.14

URLRequest

-0.14

Ã²ng

-0.14

pes

-0.14

OPS

-0.14

 zost

-0.14

POSITIVE LOGITS

ivan

0.17

reau

0.15

 Salmon

0.14

Viv

0.14

keh

0.13

{}.

0.13

.Rectangle

0.13

eways

0.13

mage

0.13

xa

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.