INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

amma

-0.15

zek

-0.15

.XR

-0.15

ovich

-0.15

_notifier

-0.14

Ø³Ø·

-0.14

 Spirits

-0.14

-0.13

ello

-0.13

geh

-0.13

POSITIVE LOGITS

 Huss

0.16

eday

0.15

Ø³Ø¯

0.15

ãĥ«ãĥī

0.15

anim

0.14

lint

0.14

Gu

0.14

 ÑģÐ¿ÑĢÑı

0.14

oucher

0.14

zier

0.14

Activations Density 0.010%

No Comments

No Known Activations