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

urat

-0.18

uras

-0.16

inda

-0.15

ddit

-0.15

azzo

-0.15

-LAST

-0.15

-0.14

legg

-0.14

ãĥ¼ãĤ¹

-0.14

 Ð²ÐµÐ´

-0.14

POSITIVE LOGITS

 Dress

0.15

uc

0.15

æĬĺ

0.14

Ð±Ð°Ð²

0.14

ex

0.14

gre

0.13

KHR

0.13

 Hack

0.13

 infl

0.13

ĸ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.