INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

idge

-0.17

âĢ«

-0.16

inois

-0.15

orges

-0.15

ãĥ¯ãĤ¤ãĥĪ

-0.15

elon

-0.15

prit

-0.14

ensem

-0.14

áº»

-0.14

exion

-0.14

POSITIVE LOGITS

ÙĬÙĥÙĬ

0.14

 fluid

0.14

-install

0.14

arr

0.14

ÄĽst

0.14

 Cypress

0.14

 interven

0.13

att

0.13

 Panel

0.13

 Estr

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.