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

 nearby

-0.15

Sug

-0.15

lias

-0.15

Fog

-0.14

meric

-0.14

 Ð¤ÐµÐ´ÐµÑĢÐ°

-0.14

 muse

-0.14

essian

-0.13

igin

-0.13

 permalink

-0.13

POSITIVE LOGITS

 Hyde

0.16

bler

0.16

antan

0.15

ieder

0.15

oll

0.14

oleans

0.14

 Cunningham

0.14

fty

0.14

omore

0.14

 Academy

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.