INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

kara

-0.15

forme

-0.15

rise

-0.14

memiÅŁ

-0.14

pec

-0.14

ReadStream

-0.13

ãģ¾ãģ¾

-0.13

 invites

-0.13

uci

-0.13

 surre

-0.13

POSITIVE LOGITS

see

0.17

0.16

 site

0.15

 town

0.15

 sunny

0.14

 rendez

0.14

empt

0.14

lbl

0.14

Æł

0.14

 Sanayi

0.13

Activations Density 0.113%

No Comments

No Known Activations