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

swick

-0.15

forum

-0.15

fak

-0.14

 kalk

-0.13

brief

-0.13

 bere

-0.13

bere

-0.13

bst

-0.13

 Incre

-0.13

_nums

-0.13

POSITIVE LOGITS

 inspection

0.29

 viol

0.28

 Inspection

0.26

 violation

0.26

 violations

0.26

 inspections

0.25

 inspected

0.24

-viol

0.24

 restaurants

0.24

 establishments

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.