INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ð¸Ð¼Ð¾

-0.15

.Interop

-0.15

emek

-0.15

chap

-0.14

.Enum

-0.14

Latch

-0.14

»¿

-0.14

 silence

-0.14

arden

-0.13

alg

-0.13

POSITIVE LOGITS

now

0.57

 ÑĤÐµÐ¿ÐµÑĢÑĮ

0.48

now

0.41

Now

0.41

 ahora

0.38

 agora

0.38

Now

0.36

NOW

0.35

 ìĿ´ìłľ

0.35

 à¤ħà¤¬

0.34

Activations Density 0.418%

No Comments

No Known Activations