INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

any

-0.16

OOSE

-0.16

 that

-0.15

ATALOG

-0.14

 such

-0.14

icket

-0.14

 finally

-0.14

try

-0.14

POSITIVE LOGITS

ftime

0.16

Ã¡bado

0.16

Ð¾ÑĤÐ¸

0.15

neau

0.14

Ä±ndÄ±r

0.14

.DEFINE

0.14

ahas

0.14

ÑĥÐ²Ð°Ð½Ð½Ñı

0.13

vertime

0.13

ElapsedTime

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.