INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

erece

-0.18

itas

-0.15

urma

-0.15

 golf

-0.14

objectId

-0.14

anske

-0.14

bitset

-0.14

isa

-0.14

bjerg

-0.14

abella

-0.13

POSITIVE LOGITS

 Municip

0.15

 parallel

0.15

om

0.14

parallel

0.14

roe

0.14

 dÃ¶n

0.13

 joystick

0.13

 Dynamo

0.13

QualifiedName

0.13

 Parallel

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.