INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ï»¿↵↵

-0.16

ynn

-0.15

bsolute

-0.15

ereo

-0.15

mere

-0.15

zia

-0.15

vern

-0.15

 Beginners

-0.14

.shtml

-0.14

inos

-0.14

POSITIVE LOGITS

emax

0.15

tod

0.14

Sin

0.14

egers

0.13

Nu

0.13

rex

0.13

libs

0.13

erg

0.13

/*----------------------------------------------------------------------------

0.13

uÅ¡

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.