INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ardash

-0.16

Nut

-0.14

illi

-0.14

urat

-0.14

elon

-0.14

LOT

-0.14

 Eisen

-0.14

ovny

-0.13

RC

-0.13

ienie

-0.13

POSITIVE LOGITS

ÅŁi

0.17

_PRIORITY

0.15

æ·¡

0.15

ÙĪØ´

0.15

Ð¼ÐµÑĤÑĮ

0.15

çĤī

0.15

å¾®

0.14

dess

0.14

.datatables

0.14

 Vend

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.