INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

alink

-0.16

rnd

-0.16

imming

-0.14

at

-0.14

maries

-0.14

amburg

-0.14

inters

-0.14

roti

-0.14

py

-0.14

bies

-0.13

POSITIVE LOGITS

stance

0.19

STANCE

0.19

 Ð±ÑĥÑĤÐ¸

0.18

 happens

0.18

 coinc

0.17

auer

0.17

toBe

0.17

 upon

0.17

Upon

0.17

Ð»ÐµÐ²

0.16

Activations Density 0.019%

No Comments

No Known Activations