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

ç²¾

-0.15

ovÃŃ

-0.15

Ã©ment

-0.15

semb

-0.14

-↵↵

-0.14

wend

-0.14

é§

-0.14

 ç²¾

-0.13

PF

-0.13

(PC

-0.13

POSITIVE LOGITS

~(

0.20

--

0.17

—

0.17

eka

0.16

~=

0.15

Job

0.15

cir

0.15

aka

0.14

agli

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.