INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 aktual

-0.17

 REGARD

-0.14

 eskort

-0.14

^.

-0.14

/lg

-0.13

kli

-0.13

 Gore

-0.13

ãĤ¦ãĤ¹

-0.13

.uml

-0.13

ICLES

-0.13

POSITIVE LOGITS

 Party

0.17

izi

0.17

 Bahamas

0.16

 party

0.15

Bah

0.15

ETH

0.15

 Chair

0.15

 Cabinet

0.15

 chairs

0.15

 chair

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.