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

YLON

-0.18

 simply

-0.16

OUCH

-0.16

 darn

-0.15

ÑĳÐ½

-0.15

 Heck

-0.15

rtl

-0.15

adge

-0.14

odies

-0.14

Hell

-0.14

POSITIVE LOGITS

 Young

0.20

--↵

0.18

cos

0.18

Sea

0.17

Cos

0.17

cos

0.17

Young

0.17

cus

0.17

SEA

0.16

 Nick

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.