INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ride

-0.14

dem

-0.14

inf

-0.14

rk

-0.14

zem

-0.14

ides

-0.14

ad

-0.13

IDEO

-0.13

 Evil

-0.13

raz

-0.13

POSITIVE LOGITS

æ³¡

0.18

ungs

0.15

otta

0.15

ioni

0.15

 NavLink

0.14

pek

0.14

/xhtml

0.14

iones

0.14

emade

0.13

xba

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.