INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

angan

-0.16

ifu

-0.16

erb

-0.16

illard

-0.15

belt

-0.14

ÐµÑĢÑĭ

-0.14

elt

-0.14

 writ

-0.14

 thro

-0.14

Enumerator

-0.14

POSITIVE LOGITS

dera

0.16

\grid

0.15

verity

0.15

assa

0.14

ä¹İ

0.14

rav

0.14

ootball

0.14

ãģ£ãģı

0.14

blem

0.14

atik

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.