INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Arch

-0.14

isch

-0.14

 ↵↵

-0.14

 Arch

-0.14

om

-0.13

å¯¹æĸ¹

-0.13

'u

-0.13

ected

-0.13

 Oaks

-0.13

_arch

-0.13

POSITIVE LOGITS

ternet

0.15

aggi

0.15

vero

0.14

qing

0.14

borg

0.14

äº

0.13

 Wich

0.13

vern

0.13

ourt

0.13

igor

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.