INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

umba

-0.15

ernen

-0.15

urai

-0.14

ousands

-0.14

mdl

-0.14

ylko

-0.14

izzes

-0.13

è³ŀ

-0.13

Protected

-0.13

POSITIVE LOGITS

 Gary

0.33

 Jerry

0.31

Gary

0.31

Jerry

0.29

Jan

0.19

erry

0.19

gary

0.18

jer

0.17

 keyboard

0.17

Î³

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.