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

ãĥ«ãĤ¯

-0.15

ingles

-0.15

ickets

-0.15

etary

-0.15

imals

-0.15

ialis

-0.15

ledon

-0.14

TED

-0.14

onium

-0.14

ÏĢÎ»Î±

-0.14

POSITIVE LOGITS

auc

0.16

her

0.16

oub

0.15

ill

0.15

ãĥ³ãĥĹ

0.15

 ware

0.14

icol

0.14

 Disp

0.14

disp

0.14

ukt

0.14

Activations Density 0.002%

No Comments

No Known Activations