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

infeld

-0.17

orsch

-0.15

.shtml

-0.15

owler

-0.14

nik

-0.14

áº¡n

-0.14

ulp

-0.14

INTR

-0.14

POSITIVE LOGITS

CIA

0.17

 Programming

0.16

fo

0.15

 programming

0.15

AMI

0.15

ase

0.15

bio

0.15

 alleged

0.14

 Psychological

0.14

 Computers

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.