INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

itere

-0.16

 epis

-0.14

-commercial

-0.14

itches

-0.14

 Duffy

-0.14

Î±Î½Î´

-0.14

episode

-0.13

onis

-0.13

UX

-0.13

ô

-0.13

POSITIVE LOGITS

odox

0.17

 Ø³ÙĦ

0.16

alone

0.14

_unc

0.14

 Alone

0.14

 Shel

0.13

IMER

0.13

vise

0.13

 sled

0.13

immune

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.