INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

XR

-0.16

ouncer

-0.15

agine

-0.15

ipple

-0.15

iences

-0.14

æĤł

-0.14

 Poll

-0.14

orners

-0.13

á»ĭnh

-0.13

oÅĻ

-0.13

POSITIVE LOGITS

amen

0.18

IllegalArgumentException

0.15

ocom

0.15

lemen

0.15

utt

0.15

inki

0.15

deki

0.14

Wat

0.14

 combined

0.14

INF

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.