INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ongan

-0.16

Fir

-0.14

áº§m

-0.14

 significantly

-0.14

oreach

-0.14

 dich

-0.14

ith

-0.13

istrovstvÃŃ

-0.13

sed

-0.13

Ã³ÅĤ

-0.13

POSITIVE LOGITS

oyer

0.17

-collapse

0.15

ë²Į

0.14

å¼ĺ

0.14

olu

0.14

 Brennan

0.14

TypeDef

0.13

ahoo

0.13

 Kunst

0.13

uttle

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.