INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

quee

-0.15

ÏĩÎ·

-0.14

pes

-0.14

æ¯«

-0.14

ende

-0.14

ugo

-0.14

 Pazar

-0.14

elen

-0.14

editable

-0.14

 JpaRepository

-0.14

POSITIVE LOGITS

eways

0.15

clr

0.15

prise

0.14

holm

0.14

atro

0.14

mage

0.14

0.13

 gardens

0.13

è½

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.