INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

.Sdk

-0.15

æ·

-0.15

.AWS

-0.15

solete

-0.14

 Natur

-0.14

 Powell

-0.14

é®®

-0.14

ë©ĺ

-0.14

ÙĳÙĩ

-0.14

alth

-0.13

POSITIVE LOGITS

 Jesus

0.19

Jud

0.17

 betr

0.16

 maybe

0.15

 perhaps

0.15

 naming

0.15

 illum

0.14

 Ø¨Ø§ÙĤ

0.14

 judgment

0.14

 Easter

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.