INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 ours

-0.15

OMPI

-0.14

Ìģc

-0.14

Ð®ÐĽ

-0.14

 Truman

-0.14

ombok

-0.14

hma

-0.13

etchup

-0.13

 behaviors

-0.13

 è©ķä¾¡

-0.13

POSITIVE LOGITS

wen

0.15

anst

0.15

uz

0.15

 bathtub

0.15

amaged

0.14

iddle

0.14

COVID

0.13

elsen

0.13

quote

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.