INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

annie

-0.14

 Antar

-0.14

plat

-0.14

atab

-0.14

enever

-0.14

Ð³Ð¾Ð´

-0.14

 Wheels

-0.13

ÐµÐ½ÑĤÑĥ

-0.13

kola

-0.13

/OR

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

à¹Īà¸Ńà¸Ļ

0.17

ħn

0.17

Blocking

0.15

 tear

0.15

langs

0.15

oment

0.13

eeper

0.13

pillar

0.13

 barric

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.