INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

etail

-0.16

iver

-0.15

ital

-0.15

ForRow

-0.14

ent

-0.14

 Sheffield

-0.14

tha

-0.13

ucher

-0.13

enth

-0.13

ynchronously

-0.13

POSITIVE LOGITS

anvas

0.16

oure

0.16

audit

0.15

ahat

0.15

anne

0.15

ãĥ¼ãĤ

0.14

regon

0.14

Ĥ¤

0.14

 ÑĢÐ°ÑģÑĤ

0.14

 Marketable

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.