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

itm

-0.17

enheim

-0.15

.ly

-0.14

assin

-0.13

agina

-0.13

.apps

-0.13

 NOTICE

-0.13

Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

-0.13

anzi

-0.13

insn

-0.13

POSITIVE LOGITS

ote

0.15

ulan

0.14

ikip

0.13

åĢĻ

0.13

 render

0.13

URAL

0.13

 proposal

0.13

 expression

0.13

 Unity

0.13

 conc

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.