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

ture

-0.17

å¯Ħ

-0.15

csr

-0.14

ote

-0.14

bay

-0.14

 budget

-0.14

zie

-0.14

otten

-0.13

olin

-0.13

ulty

-0.13

POSITIVE LOGITS

 older

0.18

ãģĵãĤĵãģ«ãģ¡ãģ¯

0.17

rawer

0.17

OLDER

0.17

vester

0.17

 oldest

0.16

MLElement

0.15

 Older

0.15

 Ã¤l

0.15

oras

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.