INDEX

Explanations

elements of mathematical equations or expressions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

apan

-0.16

Zub

-0.15

Clo

-0.15

Roh

-0.15

raz

-0.15

 hypoth

-0.15

bud

-0.14

cken

-0.14

.TabStop

-0.14

 Buch

-0.14

POSITIVE LOGITS

paged

0.16

oby

0.15

eger

0.14

adro

0.14

äº

0.14

 dinh

0.14

ãĥªãĥ¼

0.14

isay

0.14

rece

0.14

Activations Density 0.056%

elements of mathematical equations or expressions

No Comments

No Known Activations