INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

è³¢

-0.15

iesen

-0.15

 Ä°b

-0.14

èĥŀ

-0.13

ÑģÑıÑĤ

-0.13

AGON

-0.13

Ã©n

-0.13

-caption

-0.13

chalk

-0.13

POSITIVE LOGITS

 fading

0.15

onor

0.15

ora

0.15

ekler

0.14

oran

0.14

Fay

0.14

 Plastic

0.14

icket

0.13

 Daly

0.13

 Laboratories

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.