INDEX

Explanations

mathematical expressions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

CONNECT

-0.15

aleb

-0.14

ibraltar

-0.14

GINE

-0.14

ifen

-0.13

inue

-0.13

YSTEM

-0.13

 dosp

-0.13

\Collections

-0.13

esco

-0.13

POSITIVE LOGITS

odont

0.16

onical

0.15

omed

0.15

atti

0.14

unal

0.14

chedulers

0.13

 Feet

0.13

avers

0.13

ental

0.13

Activations Density 0.199%

mathematical expressions and equations

No Comments

No Known Activations