INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

benh

-0.16

UED

-0.14

ÅĻi

-0.14

åª

-0.14

orm

-0.14

quiv

-0.14

OLT

-0.14

oS

-0.14

ibold

-0.13

ÙĨÚ¯ÛĮ

-0.13

POSITIVE LOGITS

unan

0.16

 bundle

0.15

 bundles

0.14

olumn

0.14

 Bundle

0.14

 firms

0.14

COMMAND

0.13

 Econ

0.13

vat

0.13

estroy

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.