INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

_FOREACH

-0.15

Ð¾ÑĤÑĮ

-0.14

uzzle

-0.14

 æī

-0.13

serrat

-0.13

overy

-0.13

å¹ķ

-0.13

roken

-0.13

å¤Ħ

-0.13

ATA

-0.13

POSITIVE LOGITS

Ä±sÄ±ndan

0.15

hor

0.14

hower

0.14

Å¾ÃŃ

0.14

auer

0.14

geist

0.14

cuk

0.14

andler

0.14

ander

0.13

ourt

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.