INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

inq

-0.15

((↵

-0.15

ulp

-0.15

obec

-0.14

 discrepan

-0.13

DATED

-0.13

ftar

-0.13

StateException

-0.13

fak

-0.13

POSITIVE LOGITS

¬Ĥ

0.15

Collections

0.15

 Bever

0.15

iliz

0.15

apos

0.15

Automatic

0.15

automatic

0.14

coord

0.14

nest

0.14

 Burl

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.