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

itere

-0.15

ahy

-0.14

ÑĮÑĤÐµ

-0.14

 puerto

-0.14

uby

-0.13

å¯Ħ

-0.13

Äł

-0.13

riendly

-0.13

IPH

-0.13

 Welch

-0.13

POSITIVE LOGITS

 meantime

0.19

 beneath

0.17

sav

0.15

-vs

0.15

 outr

0.15

 gold

0.14

eg

0.14

undle

0.14

ie

0.14

 gilt

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.