INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

eder

-0.18

 Hastings

-0.15

bet

-0.15

 Emerson

-0.15

 Mandela

-0.14

æīĭãģ«

-0.14

 Agricult

-0.13

mand

-0.13

amet

-0.13

POSITIVE LOGITS

baugh

0.17

.EventQueue

0.16

ording

0.15

à¸´à¸©

0.15

urge

0.15

optera

0.15

å¿Ĺ

0.14

oke

0.14

ÑĢÐµÐ´

0.13

Activations Density 0.089%

No Comments

No Known Activations