INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Scalar

-0.14

ÐºÐ¸Ð´

-0.13

azines

-0.13

emann

-0.13

esters

-0.13

ETYPE

-0.13

SEL

-0.13

ftp

-0.13

THR

-0.13

.mvp

-0.13

POSITIVE LOGITS

.hy

0.15

oco

0.14

atri

0.14

/Dk

0.14

inton

0.14

adam

0.14

bens

0.14

 Ages

0.14

hq

0.13

 upstream

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.