INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Jvm

-0.17

ema

-0.17

ngen

-0.17

emas

-0.16

gis

-0.16

pper

-0.16

indre

-0.15

ìĦĿ

-0.15

cran

-0.14

usz

-0.14

POSITIVE LOGITS

stit

0.15

Gon

0.15

iferay

0.15

IfNeeded

0.14

 svens

0.14

DG

0.14

rak

0.14

idth

0.14

Ã©ny

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.