INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

noinspection

-0.15

 pylint

-0.15

Ø§ÙĪÙĩ

-0.15

ith

-0.14

frauen

-0.14

irim

-0.13

tsky

-0.13

endra

-0.13

 unint

-0.12

 //!<

-0.12

POSITIVE LOGITS

 yeah

0.17

eton

0.16

uzzer

0.15

 /↵

0.14

oyal

0.13

emas

0.13

_MAY

0.13

éĿĴ

0.13

 Renew

0.13

ataloader

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.