INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rep

-0.15

Han

-0.15

earer

-0.14

çı¾

-0.14

à¹ģà¸Ĥ

-0.14

sticky

-0.13

Rep

-0.13

jmp

-0.13

repid

-0.13

POSITIVE LOGITS

erne

0.18

uce

0.16

ASIC

0.15

uÄį

0.15

.crm

0.14

CCA

0.14

æ¦

0.14

[maxn

0.14

uze

0.14

ccd

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.