INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lane

-0.15

_lane

-0.15

inside

-0.15

 inside

-0.15

-0.14

aims

-0.14

+E

-0.14

legalArgumentException

-0.14

quila

-0.14

Ã©nÃ©

-0.14

POSITIVE LOGITS

 Away

0.22

 away

0.18

kaar

0.15

agini

0.15

atinum

0.15

_PM

0.14

-away

0.14

islav

0.14

ItemAt

0.14

aju

0.13

Activations Density 0.011%

No Comments

No Known Activations