INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

hetto

-0.16

-0.15

PullParser

-0.14

-tm

-0.14

Ä±ÅŁÄ±k

-0.13

Å¡ti

-0.13

eger

-0.13

tein

-0.13

ume

-0.13

POSITIVE LOGITS

 Over

0.28

 over

0.27

Over

0.25

over

0.23

 overs

0.22

 OVER

0.21

-over

0.21

 Ã¶ver

0.21

 sobre

0.20

overs

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.