INDEX

Explanations

queries related to data manipulation and processing in databases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Suff

-0.16

pte

-0.16

warf

-0.15

 recip

-0.15

worth

-0.14

VES

-0.14

imitive

-0.14

Ĩ

-0.14

wide

-0.13

VED

-0.13

POSITIVE LOGITS

ebi

0.16

/goto

0.16

OMPI

0.15

eb

0.15

indows

0.14

ulong

0.14

vig

0.14

.lab

0.14

egin

0.14

idden

0.14

Activations Density 0.076%

queries related to data manipulation and processing in databases

No Comments

No Known Activations