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

cela

-0.15

_BINARY

-0.13

 Housing

-0.13

 ring

-0.13

ÂĽ

-0.13

cls

-0.13

å®¿

-0.13

 Overs

-0.13

 denial

-0.13

 cocks

-0.13

POSITIVE LOGITS

 posture

0.27

 fatigue

0.25

Fat

0.24

 upright

0.23

Fat

0.23

fat

0.23

 participants

0.23

 taped

0.21

 participant

0.20

å§¿

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.