INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

asive

-0.16

bil

-0.15

qli

-0.15

 Ð¿ÑĢÐ¸Ð¿

-0.14

dsl

-0.14

nev

-0.14

Ã¹a

-0.14

iesel

-0.14

-indent

-0.14

 Ð´Ð¾ÑģÑĤ

-0.14

POSITIVE LOGITS

bart

0.17

Pur

0.16

 abst

0.15

 abuse

0.15

beg

0.15

abi

0.15

Dub

0.14

 alcohol

0.14

 sober

0.14

 interfer

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.