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

 demonstr

-0.16

rement

-0.15

yah

-0.15

ixture

-0.14

Sez

-0.14

 Duffy

-0.14

igor

-0.14

 Dent

-0.13

POSITIVE LOGITS

WindowSize

0.15

xBA

0.14

%D

0.14

 opak

0.14

ahl

0.14

íĺĳ

0.13

blade

0.13

TestMethod

0.13

 Malone

0.13

Åį

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.