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

annis

-0.16

ekli

-0.14

 spanish

-0.14

 Reverse

-0.14

 gating

-0.13

 actual

-0.13

Odd

-0.13

ãĥĲãĤ¹

-0.13

sted

-0.13

jes

-0.13

POSITIVE LOGITS

 Lage

0.15

ULSE

0.14

 Stunden

0.14

-sector

0.14

 å½

0.14

/display

0.14

lete

0.14

Ð¾ÐºÐµ

0.14

emiz

0.13

 Fleming

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.