INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Launcher

-0.13

jal

-0.13

ÙĦÙĥØªØ±

-0.13

Jeh

-0.13

WAYS

-0.13

rong

-0.13

beth

-0.13

_reload

-0.13

earch

-0.12

Modes

-0.12

POSITIVE LOGITS

Io

0.31

 sensors

0.27

 sensor

0.26

IoT

0.25

Io

0.24

 Sensor

0.23

 Sensors

0.23

 backend

0.21

sen

0.20

 devices

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.